http://mickey.ifp.illinois.edu/speechWiki/index.php?title=Special:Contributions/Mark_Hasegawa-Johnson&feed=atom&limit=50&target=Mark_Hasegawa-Johnson&year=&month=SpeechWiki - User contributions [en]2024-03-29T12:39:10ZFrom SpeechWikiMediaWiki 1.16.5http://mickey.ifp.illinois.edu/speechWiki/index.php/ProjectsProjects2013-02-19T15:53:30Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>Here are some projects that [[SST People]] are working on. For another view, see our [http://www.isle.uiuc.edu/pubs Publications].<br />
<br />
===SST Group Meetings=== <br />
<br />
* [[SST Group Meetings]]<br />
<br />
===Phonetics, Phonology, Semantics=== <br />
<br />
; Prosody and Phonology in Automatic Speech Recognition (Landmark-Based Speech Recognition)<br />
: [[landmarks09F| Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/research/landmarks.html Landmark-Based Speech Recognition]<br />
: [http://www.isle.uiuc.edu/research/prosody_of_disfluency.html Prosody of Disfluency] <br />
<br />
; Very Large Corpus ASR/ Mixed-Units ASR<br />
: [[:Category:Fisher_Experiments|Large Vocabulary speech recognition using mixed units on fisher corpus]] <br />
<br />
; [[articulatory_feature_transcription|Articulatory Feature Transcription]]<br />
: [[Transcription_Guidelines|Transcription Guidelines]]<br />
: [[Phone-to-Feature_Mapping|Phone-to-Feature Mapping]]<br />
: [[Meeting_Summaries|Meeting Summaries]]<br />
: [[Resources|Resources]]<br />
<br />
=== Group dynamics and Discourse ===<br />
<br />
; GroupScope --- Dynamics of Medium-Sized Groups<br />
: [[GroupScope]]<br />
<br />
===Language Acquisition, Language Contact, Variability, and Disability===<br />
<br />
; Multi-Dialect Speech Recognition and Machine Translation for Qatari Broadcast TV<br />
: [[Multi Dialect Arabic]]<br />
<br />
; Cross-Language Transfer Learning<br />
: [[Linguistic Diversity References]]<br />
: [http://hlt.i2r.a-star.edu.sg/starchallenge Star Challenge competition]<br />
<br />
; Dynamics of Second Language Fluency<br />
: [http://serrano.ai.uiuc.edu/CRI/ Group Meeting Schedules and Slides]<br />
: [http://www.isle.uiuc.edu/research/fluency.html Description]<br />
: [[Dynamics of Second Language Fluency Data Description|Data Description]]<br />
<br />
; Universal Access<br />
: [[dysarthria09|Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/ua/index.html Description]<br />
: [http://www.isle.uiuc.edu/UASpeech UASpeech Database]<br />
<br />
===Multimodal Fusion, Speech and Non-Speech===<br />
<br />
; Audiovisual Event Detection and Visualization<br />
: [[compaudition09| Group Meeting Schedules and Slides]]<br />
: [[acoustic_events_papers| Papers]]<br />
: [[Visualization Experiments]]<br />
<br />
; Mobile Platform Acoustic-Frequency Environmental Tomography (was Dereverberation)<br />
: [[compaudition09| Group Meeting Schedules]]<br />
: [[Dereverberation Project| Project Status and Working Notes]]<br />
<br />
; Audiovisual Speech Recognition<br />
: [http://www.isle.uiuc.edu/research/audiovisual.html Description]<br />
: [http://www.isle.uiuc.edu/AVICAR/ AVICAR Database]<br />
<br />
<br />
==See also==<br />
* [http://www.isle.illinois.edu/sst/pubs/ SST publications]<br />
* [http://www.isle.illinois.edu/sst/ SST group web page]<br />
* [[Special:Upload]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/ProjectsProjects2013-02-19T15:52:19Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>Here are some projects that [[SST People]] are working on. For another view, see our [http://www.isle.uiuc.edu/pubs Publications].<br />
<br />
===SST Group Meetings=== <br />
<br />
* [[SST Group Meetings]]<br />
<br />
===Phonetics, Phonology, Semantics=== <br />
<br />
; Prosody and Phonology in Automatic Speech Recognition (Landmark-Based Speech Recognition)<br />
: [[landmarks09F| Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/research/landmarks.html Landmark-Based Speech Recognition]<br />
: [http://www.isle.uiuc.edu/research/prosody_of_disfluency.html Prosody of Disfluency] <br />
<br />
; Very Large Corpus ASR/ Mixed-Units ASR<br />
: [[:Category:Fisher_Experiments|Large Vocabulary speech recognition using mixed units on fisher corpus]] <br />
<br />
; [[articulatory_feature_transcription|Articulatory Feature Transcription]]<br />
: [[Transcription_Guidelines|Transcription Guidelines]]<br />
: [[Phone-to-Feature_Mapping|Phone-to-Feature Mapping]]<br />
: [[Meeting_Summaries|Meeting Summaries]]<br />
: [[Resources|Resources]]<br />
<br />
=== Group dynamics and Discourse ===<br />
<br />
; GroupScope --- Dynamics of Medium-Sized Groups<br />
: [[GroupScope]]<br />
<br />
===Language Acquisition, Language Contact, Variability, and Disability===<br />
<br />
; Multi-Dialect Speech Recognition and Machine Translation for Qatari Broadcast TV<br />
: [[Multi Dialect Arabic]]<br />
<br />
; Cross-Language Transfer Learning<br />
: [[Linguistic Diversity References]]<br />
: [http://hlt.i2r.a-star.edu.sg/starchallenge Star Challenge competition]<br />
<br />
; Dynamics of Second Language Fluency<br />
: [http://serrano.ai.uiuc.edu/CRI/ Group Meeting Schedules and Slides]<br />
: [http://www.isle.uiuc.edu/research/fluency.html Description]<br />
: [[Dynamics of Second Language Fluency Data Description|Data Description]]<br />
<br />
; Universal Access<br />
: [[dysarthria09|Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/ua/index.html Description]<br />
: [http://www.isle.uiuc.edu/UASpeech UASpeech Database]<br />
<br />
===Multimodal Fusion, Speech and Non-Speech===<br />
<br />
; Audiovisual Event Detection and Visualization<br />
: [[compaudition09| Group Meeting Schedules and Slides]]<br />
: [[acoustic_events_papers| Papers]]<br />
: [[Visualization Experiments]]<br />
<br />
; Mobile Platform Acoustic-Frequency Environmental Tomography (was Dereverberation)<br />
: [[compaudition09| Group Meeting Schedules]]<br />
: [[Dereverberation Project| Project Status and Working Notes]]<br />
<br />
; Audiovisual Speech Recognition<br />
: [http://www.isle.uiuc.edu/research/audiovisual.html Description]<br />
: [http://www.isle.uiuc.edu/AVICAR/ AVICAR Database]<br />
<br />
<br />
==See also==<br />
* [http://www.isle.illinois.edu/sst/pubs/ SST publications]<br />
* [http://www.isle.illinois.edu/sst/ SST group web page]<br />
* [[commons:Special:Upload]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-09-12T15:49:56Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Semitic Language Resources]]<br />
<br />
<br />
=Meetings at Illinois, Fall 2010=<br />
<br />
Regular research meetings have been scheduled in 2169 Beckman, in Urbana, 3:30-4:30 PM, Tuesdays in fall semester 2010. These will be superseded<br />
international meetings if the international meeting schedule can be established.<br />
<br />
; Tuesday August 24, 2010, 2169 Beckman<br />
: Introductions and overview of proposed research<br />
<br />
; Tuesday August 31, 2010, 2169 Beckman<br />
: Basics of Speech Recognition<br />
: Coordinator: MH<br />
: Reading: Rabiner, Proceedings of the IEEE, 1989<br />
<br />
; Tuesday September 14, 2010, 2169 Beckman<br />
: Basics of Arabic Morphophonology<br />
: Coordinator: EB<br />
: [http://www.isle.illinois.edu/papers/Mustafawi-thesis.pdf An Optimality Theoretic Approach to Variable Consonant Alternations in Qatari Arabic,] Eiman Mustafawi<br />
: [http://www.isle.illinois.edu/papers/mccarthy05.pdf Morphology,] McCarthy<br />
<br />
; Tuesday October 5, 2010, 2169 Beckman<br />
: Basics of Machine Translation<br />
: Coordinator: RG<br />
<br />
; Tuesday October 19, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Rania Al-Sabbagh<br />
<br />
; Tuesday November 2, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Sujeeth Bharadwaj<br />
<br />
; Tuesday November 16, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Chen Li<br />
<br />
; Tuesday November 30, 2010, 2169 Beckman<br />
: Wrap-up and prospectus</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-09-04T13:49:40Z<p>Mark Hasegawa-Johnson: /* September 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===October 2010===<br />
<br />
; October 5<br />
:12:30 - 2:00, Beckman 2169<br />
:Arthur Kantor, defense practice<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21, 12:00-2:00<br />
:12:30 - 2:00, Beckman 2169<br />
: Interspeech practice talks<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
:Tim Mahrt progress report<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
:Discussion of competing definitions of the word "category." Papers include<br />
:[http://jmlr.csail.mit.edu/papers/volume8/li07a/li07a.pdf A Nonparametric Statistical Approach...], Li, Ray and Lindsay<br />
:[http://www.isle.illinois.edu/papers/rosch1976.pdf Rosch 1976]<br />
:[http://www.isle.illinois.edu/papers/holt-2004.pdf Holt 2004]<br />
:[http://www.isle.illinois.edu/papers/Labov-vases.pdf Labov Vases]<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-09-02T16:40:38Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===October 2010===<br />
<br />
; October 5<br />
:12:30 - 2:00, Beckman 2169<br />
:Arthur Kantor, defense practice<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21, 12:00-2:00<br />
:12:30 - 2:00, Beckman 2169<br />
: Interspeech practice talks<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
:Tim Mahrt progress report<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
:Discussion of competing definitions of the word "category." Papers include<br />
:[http://jmlr.csail.mit.edu/papers/volume8/li07a/li07a.pdf A Nonparametric Statistical Approach...], Li, Ray and Lindsay<br />
:[http://www.isle.illinois.edu/papers/rosch1976.pdf Rosch 1976]<br />
:[http://www.isle.illinois.edu/papers/holt-2004.pdf Holt 2004]<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-09-01T15:51:20Z<p>Mark Hasegawa-Johnson: /* Meeting Schedule, Fall 2010 */</p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Semitic Language Resources]]<br />
<br />
=Meeting Schedule, Fall 2010=<br />
<br />
; Tuesday August 24, 2010, 2169 Beckman<br />
: Introductions and overview of proposed research<br />
<br />
; Tuesday August 31, 2010, 2169 Beckman<br />
: Basics of Speech Recognition<br />
: Coordinator: MH<br />
: Reading: Rabiner, Proceedings of the IEEE, 1989<br />
<br />
; Tuesday September 14, 2010, 2169 Beckman<br />
: Basics of Arabic Morphophonology<br />
: Coordinator: EB<br />
: [http://www.isle.illinois.edu/papers/Mustafawi-thesis.pdf An Optimality Theoretic Approach to Variable Consonant Alternations in Qatari Arabic,] Eiman Mustafawi<br />
: [http://www.isle.illinois.edu/papers/mccarthy05.pdf Morphology,] McCarthy<br />
<br />
; Tuesday October 5, 2010, 2169 Beckman<br />
: Basics of Machine Translation<br />
: Coordinator: RG<br />
<br />
; Tuesday October 19, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Rania Al-Sabbagh<br />
<br />
; Tuesday November 2, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Sujeeth Bharadwaj<br />
<br />
; Tuesday November 16, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Chen Li<br />
<br />
; Tuesday November 30, 2010, 2169 Beckman<br />
: Wrap-up and prospectus</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-09-01T15:50:53Z<p>Mark Hasegawa-Johnson: /* Meeting Schedule, Fall 2010 */</p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Semitic Language Resources]]<br />
<br />
=Meeting Schedule, Fall 2010=<br />
<br />
; Tuesday August 24, 2010, 2169 Beckman<br />
: Introductions and overview of proposed research<br />
<br />
; Tuesday August 31, 2010, 2169 Beckman<br />
: Basics of Speech Recognition<br />
: Coordinator: MH<br />
: Reading: Rabiner, Proceedings of the IEEE, 1989<br />
<br />
; Tuesday September 14, 2010, 2169 Beckman<br />
: Basics of Arabic Morphophonology<br />
: Coordinator: EB<br />
: [http://www.ifp.illinois.edu/papers/Mustafawi-thesis.pdf An Optimality Theoretic Approach to Variable Consonant Alternations in Qatari Arabic,] Eiman Mustafawi<br />
: [http://www.ifp.illinois.edu/papers/mccarthy05.pdf Morphology,] McCarthy<br />
<br />
; Tuesday October 5, 2010, 2169 Beckman<br />
: Basics of Machine Translation<br />
: Coordinator: RG<br />
<br />
; Tuesday October 19, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Rania Al-Sabbagh<br />
<br />
; Tuesday November 2, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Sujeeth Bharadwaj<br />
<br />
; Tuesday November 16, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Chen Li<br />
<br />
; Tuesday November 30, 2010, 2169 Beckman<br />
: Wrap-up and prospectus</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-09-01T15:41:52Z<p>Mark Hasegawa-Johnson: /* Fall 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===October 2010===<br />
<br />
; October 5<br />
:12:30 - 2:00, Beckman 2169<br />
:Arthur Kantor, defense practice<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21, 12:00-2:00<br />
:12:30 - 2:00, Beckman 2169<br />
: Interspeech practice talks<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
:Tim Mahrt progress report<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
:Discussion of competing definitions of the word "category." Papers include<br />
:[http://jmlr.csail.mit.edu/papers/volume8/li07a/li07a.pdf A Nonparametric Statistical Approach...], Li, Ray and Lindsay<br />
:[http://www.isle.illinois.edu/papers/rosch1976.pdf Rosch 1976]<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-08-31T18:42:31Z<p>Mark Hasegawa-Johnson: /* Fall 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===October 2010===<br />
<br />
; October 5<br />
:12:30 - 2:00, Beckman 2169<br />
:Arthur Kantor, defense practice<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21, 12:00-2:00<br />
:12:30 - 2:00, Beckman 2169<br />
: Interspeech practice talks<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
:Tim Mahrt progress report<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
:Discussion of competing definitions of the word "category." Papers include<br />
:[http://jmlr.csail.mit.edu/papers/volume8/li07a/li07a.pdf A Nonparametric Statistical Approach...], Li, Ray and Lindsay<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-08-31T18:27:41Z<p>Mark Hasegawa-Johnson: /* September 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21<br />
: No meeting<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
:Discussion of competing definitions of the word "category." Papers include<br />
:[http://jmlr.csail.mit.edu/papers/volume8/li07a/li07a.pdf A Nonparametric Statistical Approach...], Li, Ray and Lindsay<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-08-31T18:26:18Z<p>Mark Hasegawa-Johnson: /* September 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21<br />
: No meeting<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
:Discussion of competing definitions of the word "category." Papers include<br />
:[http://jmlr.csail.mit.edu/papers/volume8/li07a/li07a.pdf A Nonparametric Statistical Approach...], Ray, Li, and Lindsay<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-08-31T17:58:55Z<p>Mark Hasegawa-Johnson: /* August 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21<br />
: No meeting<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00, Beckman 2169<br />
:Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-08-31T17:56:16Z<p>Mark Hasegawa-Johnson: /* Fall 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
Meetings Fall 2010 will be held in 2169 Beckman, 12:30-2:00PM on Tuesdays.<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21<br />
: No meeting<br />
<br />
; September 14<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; September 7<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 31<br />
:12:30 - 2:00, Beckman 2169<br />
<br />
; Tuesday, August 24, Beckman 2169<br />
:12:30 - 2:00<br />
Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-08-31T17:54:31Z<p>Mark Hasegawa-Johnson: /* September 2010 */</p>
<hr />
<div>==Fall 2010==<br />
<br />
===September 2010===<br />
<br />
; September 28<br />
: No meeting - Interspeech<br />
<br />
; September 21<br />
: No meeting<br />
<br />
; September 14<br />
<br />
; September 7<br />
<br />
===August 2010===<br />
<br />
; Tuesday, August 24;<br />
:12:30 - 2:00<br />
Jui-Ting presents<br />
<br />
==Spring and Summer 2010==<br />
<br />
<br />
===August 2010===<br />
; Tuesday August 17;<br />
:12:30 - 2:00<br />
Alina's presentation<br />
<br />
; Tuesday August 3;<br />
:12:30 - 2:00<br />
<br />
===July 2010===<br />
<br />
; Tuesday July 27;<br />
:12:30 - 2:00<br />
<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 29;<br />
:12:30 - 2:00<br />
<br />
; Tuesday June 22;<br />
:12:30 - 2:00<br />
: Jeniffer presents<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
:* [http://course.sol.lu.se/FON218/Steinhauer_et_al_1999.pdf Brain potentials indicate immediate use of prosodic cues in natural speech processing]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/SST_Group_MeetingsSST Group Meetings2010-08-27T22:11:25Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Fall, 2010==<br />
<br />
Meetings in fall 2010 will be held in 5369 Beckman, 10:30-11:30 on Monday mornings.<br />
<br />
; August 30 - three-minute research summaries<br />
<br />
; Sep 6 - Xiaodan Zhuang<br />
<br />
; Sep 13 - Arthur Kantor<br />
<br />
; Oct 4 - Harsh Vardhan Sharma<br />
<br />
; Oct 11 - Yihe Zu<br />
<br />
; Oct 17 - Jeremy Tidemann <br />
<br />
; Oct 25 - Po-Sen Huang<br />
<br />
; Nov 1 - Jui-Ting Huang<br />
<br />
; Nov 8 - Christopher Co<br />
<br />
; Nov 15 - Sujeeth Bharadwaj<br />
<br />
; Nov 29 - Sarah King</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/SST_Group_MeetingsSST Group Meetings2010-08-26T22:56:52Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Fall, 2010==<br />
<br />
; August 30, 10:30-11:30, 5369 Beckman<br />
: introductions<br />
<br />
; Sep 6, 10:30-11:30, 5369 BI<br />
: Xiaodan Zhuang<br />
<br />
; Sep 13, 10:30-11:30, 5369 BI<br />
: Jeremy Tidemann<br />
<br />
; Oct 4, 10:30-11:30, 5369 BI<br />
: Harsh Vardhan Sharma<br />
<br />
; Oct 11, 10:30-11:30, 5369 BI<br />
: Yihe Zu<br />
<br />
; Oct 17, 10:30-11:30, 5369 BI<br />
: Arthur Kantor <br />
<br />
; Oct 25, 10:30-11:30, 5369 BI<br />
: Po-Sen Huang<br />
<br />
; Nov 1, 10:30-11:30, 5369 BI<br />
: Jui-Ting Huang<br />
<br />
; Nov 8, 10:30-11:30, 5369 BI<br />
: Christopher Co<br />
<br />
; Nov 15, 10:30-11:30, 5369 BI<br />
: Sujeeth Bharadwaj<br />
<br />
; Nov 29, 10:30-11:30, 5369 BI<br />
: Sarah King</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/SST_Group_MeetingsSST Group Meetings2010-08-26T22:56:31Z<p>Mark Hasegawa-Johnson: /* Fall, 2010 */</p>
<hr />
<div>==Fall, 2010==<br />
<br />
; August 30, 10:30-11:30, 5369 Beckman<br />
: introductions<br />
<br />
; Sep 6, 10:30-11:30, 5369 BI<br />
: Xiaodan Zhuang<br />
<br />
; Sep 13, 10:30-11:30, 5369 BI<br />
: Jeremy Tideman<br />
<br />
; Oct 4, 10:30-11:30, 5369 BI<br />
: Harsh Vardhan Sharma<br />
<br />
; Oct 11, 10:30-11:30, 5369 BI<br />
: Yihe Zu<br />
<br />
; Oct 17, 10:30-11:30, 5369 BI<br />
: Arthur Kantor <br />
<br />
; Oct 25, 10:30-11:30, 5369 BI<br />
: Po-Sen Huang<br />
<br />
; Nov 1, 10:30-11:30, 5369 BI<br />
: Jui-Ting Huang<br />
<br />
; Nov 8, 10:30-11:30, 5369 BI<br />
: Christopher Co<br />
<br />
; Nov 15, 10:30-11:30, 5369 BI<br />
: Sujeeth Bharadwaj<br />
<br />
; Nov 29, 10:30-11:30, 5369 BI<br />
: Sarah King</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/SST_Group_MeetingsSST Group Meetings2010-08-26T22:52:54Z<p>Mark Hasegawa-Johnson: /* Fall, 2010 */</p>
<hr />
<div>==Fall, 2010==<br />
<br />
; August 30, 10:30-11:30, 5369 Beckman<br />
: introductions<br />
<br />
; Sep 6, 10:30-11:30, 5369 BI<br />
: Xiaodan Zhuang<br />
<br />
; Sep 13, 10:30-11:30, 5369 BI<br />
: Harsh Vardhan Sharma<br />
<br />
; Oct 4, 10:30-11:30, 5369 BI<br />
: Yihe Zu<br />
<br />
; Oct 11, 10:30-11:30, 5369 BI<br />
: Sarah King<br />
<br />
; Oct 17, 10:30-11:30, 5369 BI<br />
: Arthur Kantor <br />
<br />
; Oct 25, 10:30-11:30, 5369 BI<br />
: Po-Sen Huang<br />
<br />
; Nov 1, 10:30-11:30, 5369 BI<br />
: Jui-Ting Huang<br />
<br />
; Nov 8, 10:30-11:30, 5369 BI<br />
: Christopher Co<br />
<br />
; Nov 15, 10:30-11:30, 5369 BI<br />
: Sujeeth Bharadwaj</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/SST_Group_MeetingsSST Group Meetings2010-08-26T22:50:26Z<p>Mark Hasegawa-Johnson: Created page with "==Fall, 2010== ; August 30, 10:30-11:30, 5369 Beckman : introductions ; Sep 6, 10:30-11:30, 5369 BI : Xiaodan Zhuang ; Sep 13, 10:30-11:30, 5369 BI : Harsh Vardhan Sharma ; O..."</p>
<hr />
<div>==Fall, 2010==<br />
<br />
; August 30, 10:30-11:30, 5369 Beckman<br />
: introductions<br />
<br />
; Sep 6, 10:30-11:30, 5369 BI<br />
: Xiaodan Zhuang<br />
<br />
; Sep 13, 10:30-11:30, 5369 BI<br />
: Harsh Vardhan Sharma<br />
<br />
; Oct 4, 10:30-11:30, 5369 BI<br />
: Sarah King<br />
<br />
; Oct 11, 10:30-11:30, 5369 BI<br />
: Arthur Kantor<br />
<br />
; Oct 17, 10:30-11:30, 5369 BI<br />
: Po-Sen Huang <br />
<br />
; Oct 25, 10:30-11:30, 5369 BI<br />
: Jui-Ting Huang<br />
<br />
; Nov 1, 10:30-11:30, 5369 BI<br />
: Christopher Co<br />
<br />
; Nov 8, 10:30-11:30, 5369 BI<br />
: Sujeeth Bharadwaj</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/ProjectsProjects2010-08-26T22:45:32Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>Here are some projects that [[SST People]] are working on. For another view, see our [http://www.isle.uiuc.edu/pubs Publications].<br />
<br />
===SST Group Meetings===<br />
<br />
* [[SST Group Meetings]]<br />
<br />
===Phonetics, Phonology, Semantics===<br />
<br />
; Prosody and Phonology in Automatic Speech Recognition (Landmark-Based Speech Recognition)<br />
: [[landmarks09F| Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/research/landmarks.html Landmark-Based Speech Recognition]<br />
: [http://www.isle.uiuc.edu/research/prosody_of_disfluency.html Prosody of Disfluency] <br />
<br />
; Very Large Corpus ASR/ Mixed-Units ASR<br />
: [[:Category:Fisher_Experiments|Large Vocabulary speech recognition using mixed units on fisher corpus]] <br />
<br />
; [[articulatory_feature_transcription|Articulatory Feature Transcription]]<br />
: [[Transcription_Guidelines|Transcription Guidelines]]<br />
: [[Phone-to-Feature_Mapping|Phone-to-Feature Mapping]]<br />
: [[Meeting_Summaries|Meeting Summaries]]<br />
: [[Resources|Resources]]<br />
<br />
=== Group dynamics and Discourse ===<br />
<br />
; GroupScope --- Dynamics of Medium-Sized Groups<br />
: [[GroupScope]]<br />
<br />
===Language Acquisition, Language Contact, Variability, and Disability===<br />
<br />
; Multi-Dialect Speech Recognition and Machine Translation for Qatari Broadcast TV<br />
: [[Multi Dialect Arabic]]<br />
<br />
; Cross-Language Transfer Learning<br />
: [[Linguistic Diversity References]]<br />
: [http://hlt.i2r.a-star.edu.sg/starchallenge Star Challenge competition]<br />
<br />
; Dynamics of Second Language Fluency<br />
: [http://serrano.ai.uiuc.edu/CRI/ Group Meeting Schedules and Slides]<br />
: [http://www.isle.uiuc.edu/research/fluency.html Description]<br />
: [[Dynamics of Second Language Fluency Data Description|Data Description]]<br />
<br />
; Universal Access<br />
: [[dysarthria09|Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/ua/index.html Description]<br />
: [http://www.isle.uiuc.edu/UASpeech UASpeech Database]<br />
<br />
===Multimodal Fusion, Speech and Non-Speech===<br />
<br />
; Audiovisual Event Detection and Visualization<br />
: [[compaudition09| Group Meeting Schedules and Slides]]<br />
: [[acoustic_events_papers| Papers]]<br />
: [[Visualization Experiments]]<br />
<br />
; Mobile Platform Acoustic-Frequency Environmental Tomography (was Dereverberation)<br />
: [[compaudition09| Group Meeting Schedules]]<br />
: [[Dereverberation Project| Project Status and Working Notes]]<br />
<br />
; Audiovisual Speech Recognition<br />
: [http://www.isle.uiuc.edu/research/audiovisual.html Description]<br />
: [http://www.isle.uiuc.edu/AVICAR/ AVICAR Database]<br />
<br />
<br />
==See also==<br />
* [http://www.isle.illinois.edu/sst/pubs/ SST publications]<br />
* [http://www.isle.illinois.edu/sst/ SST group web page]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/ProjectsProjects2010-08-26T22:45:09Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>Here are some projects that [[SST People]] are working on. For another view, see our [http://www.isle.uiuc.edu/pubs Publications].<br />
<br />
===SST Group Meetings===<br />
<br />
* [SST Group Meetings 2010]<br />
<br />
===Phonetics, Phonology, Semantics===<br />
<br />
; Prosody and Phonology in Automatic Speech Recognition (Landmark-Based Speech Recognition)<br />
: [[landmarks09F| Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/research/landmarks.html Landmark-Based Speech Recognition]<br />
: [http://www.isle.uiuc.edu/research/prosody_of_disfluency.html Prosody of Disfluency] <br />
<br />
; Very Large Corpus ASR/ Mixed-Units ASR<br />
: [[:Category:Fisher_Experiments|Large Vocabulary speech recognition using mixed units on fisher corpus]] <br />
<br />
; [[articulatory_feature_transcription|Articulatory Feature Transcription]]<br />
: [[Transcription_Guidelines|Transcription Guidelines]]<br />
: [[Phone-to-Feature_Mapping|Phone-to-Feature Mapping]]<br />
: [[Meeting_Summaries|Meeting Summaries]]<br />
: [[Resources|Resources]]<br />
<br />
=== Group dynamics and Discourse ===<br />
<br />
; GroupScope --- Dynamics of Medium-Sized Groups<br />
: [[GroupScope]]<br />
<br />
===Language Acquisition, Language Contact, Variability, and Disability===<br />
<br />
; Multi-Dialect Speech Recognition and Machine Translation for Qatari Broadcast TV<br />
: [[Multi Dialect Arabic]]<br />
<br />
; Cross-Language Transfer Learning<br />
: [[Linguistic Diversity References]]<br />
: [http://hlt.i2r.a-star.edu.sg/starchallenge Star Challenge competition]<br />
<br />
; Dynamics of Second Language Fluency<br />
: [http://serrano.ai.uiuc.edu/CRI/ Group Meeting Schedules and Slides]<br />
: [http://www.isle.uiuc.edu/research/fluency.html Description]<br />
: [[Dynamics of Second Language Fluency Data Description|Data Description]]<br />
<br />
; Universal Access<br />
: [[dysarthria09|Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/ua/index.html Description]<br />
: [http://www.isle.uiuc.edu/UASpeech UASpeech Database]<br />
<br />
===Multimodal Fusion, Speech and Non-Speech===<br />
<br />
; Audiovisual Event Detection and Visualization<br />
: [[compaudition09| Group Meeting Schedules and Slides]]<br />
: [[acoustic_events_papers| Papers]]<br />
: [[Visualization Experiments]]<br />
<br />
; Mobile Platform Acoustic-Frequency Environmental Tomography (was Dereverberation)<br />
: [[compaudition09| Group Meeting Schedules]]<br />
: [[Dereverberation Project| Project Status and Working Notes]]<br />
<br />
; Audiovisual Speech Recognition<br />
: [http://www.isle.uiuc.edu/research/audiovisual.html Description]<br />
: [http://www.isle.uiuc.edu/AVICAR/ AVICAR Database]<br />
<br />
<br />
==See also==<br />
* [http://www.isle.illinois.edu/sst/pubs/ SST publications]<br />
* [http://www.isle.illinois.edu/sst/ SST group web page]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Compaudition09Compaudition092010-08-24T20:11:24Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==FODAVA, Fall 2010==<br />
<br />
FODAVA Audio Visualization Group, Fall 2010, will meet alternate Thursdays in 5369 Beckman, 3-4pm<br />
<br />
; August 26, 3-4, BI 5369<br />
: timeliner status update. final allocation of tasks remaining prior to human subjects experiments.<br />
<br />
; September 9, 2010, BI 5369<br />
: timeliner dry run for human subject experiments. Advertisement for subjects should be posted by this time, and we should be getting subject requests.<br />
<br />
; September 23, 2010, BI 5369<br />
: Mark is at Interspeech, human subjects experiments are running.<br />
<br />
; October 7, 2010, BI 5369<br />
: status update on human subjects experiments, emergency fixes<br />
<br />
; October 20, 2010 BI 5369<br />
: final wrap-up of human subject experiments, beginning of data analysis<br />
<br />
<br />
<br />
==Acoustic Events alternating with Dereverberation, Fall 2009==<br />
<br />
Computer Audition Group and Dereverberation Group will alternate Fridays, meeting 12:00-1:00pm in 2169 Beckman.<br />
<br />
<br />
; March 27<br />
: [http://www.isle.uiuc.edu/slides/2009/Tahn2009Mar27.pdf Current experimental definitions of audio salience]<br />
: [http://www.isle.uiuc.edu/papers/Lin2009Apr09.ppt Visual salience definitions]<br />
<br />
; March 20<br />
: Methods and audio examples of field recording at Willard Airport. Dave Cohen and Camille Goudeseune.<br />
: /workspace/ifp-32-2/hasegawa/data/multimodal/nonspeech/FODAVA/090216 Slides here<br />
<br />
; March 13<br />
: Beckman Open House<br />
<br />
; March 6 Acoustic Events<br />
: Auditory Psychophysics, Attention, Auditory Salience<br />
: Papers are at [[Acoustic events papers]]<br />
<br />
; Feb 27 Dereverberation<br />
: Literature review: acoustic range-finding, autonomous vehicles<br />
<br />
; Feb 20 Acoustic Events<br />
: Article: Bryce Lobdell discusses Posner and Peterson, "Attention and Cognitive Control," from Information Processing and Cognition: The Loyola Symposium, 1975<br />
: Bryce's slides are here in [http://www.isle.uiuc.edu/slides/2009/Lobdell2009Feb20.odp Open Office] format<br />
: The paper is [http://www.isle.uiuc.edu/papers/posner90.pdf here]. For username and password, send e-mail to Prof. Hasegawa-Johnson.<br />
<br />
; Feb 13 Dereverberation<br />
: Article: Sarah Borys discusses [http://scitation.aip.org/getpdf/servlet/GetPDFServlet?filetype=pdf&id=JASMAN000110000001000037000001&idtype=cvips&prog=normal Optimal focusing by spatio-temporal inverse filter. I. Basic principles,] M. Tanter, J.-F. Aubry, J. Gerber, J.-L. Thomas, and M. Fink, J. Acoust. Soc. Am. Volume 110, Issue 1, pp. 37-47 (July 2001)<br />
<br />
: Article: Sarah Borys discusses [http://scitation.aip.org/getpdf/servlet/GetPDFServlet?filetype=pdf&id=JASMAN000110000001000048000001&idtype=cvips&prog=normal Optimal focusing by spatio-temporal inverse filter. II. Experiments. Application to focusing through absorbing and reverberating media,] J.-F. Aubry, M. Tanter, J. Gerber, J.-L. Thomas, and M. Fink, J. Acoust. Soc. Am. Volume 110, Issue 1, pp. 48-58 (July 2001) <br />
<br />
:Also, be prepared to discuss possible experiments!<br />
<br />
; Feb 6 Acoustic Events<br />
: Kyungtae Kim presents audio transcriber instructions, and all of us will try the protocol<br />
<br />
; Jan 30 Dereverberation<br />
: Article: Laehoon Kim discusses [http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4067028 Precise Dereverberation Using Multichannel Linear Prediction,] M. Delcroix, T. Hikichi, and M. Miyoshi, Trans. Audio, Speech, and Language Feb. 2007 15(2):430-440<br />
<br />
; Jan 23 Acoustic Events<br />
: Planning meeting<br />
<br />
==Acoustic Events, Fall 2008==<br />
<br />
; [http://fodava.gatech.edu/node/23 FODAVA Distinguished Lecture Series]<br />
: Alexey Chervonenkis and Vladimir Vapnik<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Lin2008Dec03.ppt Audio Saliency on Spectrogram]<br />
: Kai-Hsiang Lin, 12/3/2008, 1:00, 2035 Beckman<br />
<br />
; [http://www.isle.uiuc.edu/slides/2009/Tahn2008Nov12.pdf Auditory Psychophysics]<br />
: Kyung-Tae Kim, 11/12/2008, 1:00, 2169 Beckman<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Zhuang2008Oct29.ppt Feature Analysis and Selection for Acoustic Event Detection]<br />
: Xiaodan Zhuang and Xi Zhou, 10/29/2008, 1:00, 2169 Beckman<br />
<br />
; Perceptual Salience<br />
: Dirk Bernhardt-Walther, 10/15/2008, 1:00, 2169 Beckman<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Goudeseune2008Oct01.ppt Visualizing Audio for Anomaly Detection]<br />
: Camille Goudeseune, 10/1/2008, 1:00, 2169 Beckman<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-08-24T15:20:39Z<p>Mark Hasegawa-Johnson: /* Meeting Schedule, Fall 2010 */</p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Semitic Language Resources]]<br />
<br />
=Meeting Schedule, Fall 2010=<br />
<br />
; Tuesday August 24, 2010, 2169 Beckman<br />
: Introductions and overview of proposed research<br />
<br />
; Tuesday August 31, 2010, 2169 Beckman<br />
: Basics of Speech Recognition<br />
: Coordinator: MH<br />
: Reading: Rabiner, Proceedings of the IEEE, 1989<br />
<br />
; Tuesday September 14, 2010, 2169 Beckman<br />
: Basics of Arabic Morphophonology<br />
: Coordinator: EB<br />
<br />
; Tuesday October 5, 2010, 2169 Beckman<br />
: Basics of Machine Translation<br />
: Coordinator: RG<br />
<br />
; Tuesday October 19, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Rania Al-Sabbagh<br />
<br />
; Tuesday November 2, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Sujeeth Bharadwaj<br />
<br />
; Tuesday November 16, 2010, 2169 Beckman<br />
: Research background and/or current results<br />
: Chen Li<br />
<br />
; Tuesday November 30, 2010, 2169 Beckman<br />
: Wrap-up and prospectus</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-08-24T02:09:31Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Semitic Language Resources]]<br />
<br />
=Meeting Schedule, Fall 2010=<br />
<br />
; Tuesday August 24, 2010<br />
: Introductions and overview of proposed research<br />
<br />
; Tuesday August 31, 2010<br />
: Basics of Speech Recognition<br />
: Coordinator: MH<br />
: Reading: Rabiner, Proceedings of the IEEE, 1989<br />
<br />
; Tuesday September 14, 2010<br />
: Basics of Arabic Morphophonology<br />
: Coordinator: EB<br />
<br />
; Tuesday October 5, 2010<br />
: Basics of Machine Translation<br />
: Coordinator: RG<br />
<br />
; Tuesday October 19, 2010<br />
: Research background and/or current results<br />
: Rania Al-Sabbagh<br />
<br />
; Tuesday November 2, 2010<br />
: Research background and/or current results<br />
: Sujeeth Bharadwaj<br />
<br />
; Tuesday November 16, 2010<br />
: Research background and/or current results<br />
: Sujeeth Bharadwaj<br />
<br />
; Tuesday November 30, 2010<br />
: Wrap-up and prospectus</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Semitic_Language_ResourcesSemitic Language Resources2010-07-28T23:14:54Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>A wiki list being compiled as part of our [[Multi Dialect Arabic]] project.<br />
<br />
;General Info about Language Interrelationships<br />
* [http://www.wikipedia.org Wikipedia, of course]<br />
* [http://wals.info/ World Atlas of Language Structures]<br />
<br />
; Language Data<br />
* [http://www.ldc.upenn.edu LDC, of course]<br />
* [http://alrabiya.net/ Alrabiya.net Parallel Broadcast Text in MSA and Dialect]<br />
* [http://nlp.amharic.org/ Amharic NLP website]<br />
<br />
; Software<br />
* [http://international.sakhr.com/arabic-nlp-natural-language-processing.html Sakhr]<br />
* [http://nlp.stanford.edu/software/lex-parser.shtml Stanford Parser] includes an Arabic model<br />
* [http://www1.ccls.columbia.edu/~cadim/MADA.html MADA+TOKAN]<br />
* [http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2004L02 Buckwalter]<br />
<br />
; Tutorials<br />
* [http://www.medar.info/conference_all/2009/Tutorial_1.pdf Medar tutorial] on Arabic NLP, Nizar Habash and Mona Diab<br />
* [http://www.clsp.jhu.edu/ws2002/groups/arabic/ WS02]<br />
<br />
;References about Diglossia/Variation in Spoken Arabic<br />
* Abdel-Jawad, H. R. 1981. Lexical and phonological variation in spoken Arabic in Amman. PhD dissertation University of Pennsylvania.<br />
* Blanc. 1960. Stylistic variations in spoken Arabic, in Contribution to Arabic Linguistics (ed.) by Ferguson 1964. Cambridge, Mass. pp. 81-156.<br />
* Schmit, R. W. 1975. Sociostylistic variation in spoken Egyptian Arabic: Examination of the concept of diaglossia. PhD dissertation, Brown Univ.<br />
* Shorrab. 1981. Models of socially significant linguistic variation: The case of Palestinian Arabic. PhD dissertation, State Univ. of New York at Buffalo.</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Semitic_Language_ResourcesSemitic Language Resources2010-07-28T23:11:56Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>A wiki list being compiled as part of our [[Multi Dialect Arabic]] project.<br />
<br />
;General Info about Language Interrelationships<br />
* [http://www.wikipedia.org Wikipedia, of course]<br />
* [http://wals.info/ World Atlas of Language Structures]<br />
<br />
; Language Data<br />
* [http://www.ldc.upenn.edu LDC, of course]<br />
* [http://alrabiya.net/ Alrabiya.net Parallel Broadcast Text in MSA and Dialect]<br />
* [http://nlp.amharic.org/ Amharic NLP website]<br />
<br />
; Software<br />
* [http://international.sakhr.com/arabic-nlp-natural-language-processing.html Sakhr]<br />
* [http://nlp.stanford.edu/software/lex-parser.shtml Stanford Parser] includes an Arabic model<br />
* [http://www1.ccls.columbia.edu/~cadim/MADA.html MADA+TOKAN]<br />
* [http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2004L02 Buckwalter]<br />
<br />
; Tutorials<br />
* [http://www.medar.info/conference_all/2009/Tutorial_1.pdf Medar tutorial] on Arabic NLP, Nizar Habash and Mona Diab<br />
* [http://www.ccls.columbia.edu/project/cadim-columbia-arabic-dialect-modeling CADIM]<br />
<br />
;References about Diglossia/Variation in Spoken Arabic<br />
* Abdel-Jawad, H. R. 1981. Lexical and phonological variation in spoken Arabic in Amman. PhD dissertation University of Pennsylvania.<br />
* Blanc. 1960. Stylistic variations in spoken Arabic, in Contribution to Arabic Linguistics (ed.) by Ferguson 1964. Cambridge, Mass. pp. 81-156.<br />
* Schmit, R. W. 1975. Sociostylistic variation in spoken Egyptian Arabic: Examination of the concept of diaglossia. PhD dissertation, Brown Univ.<br />
* Shorrab. 1981. Models of socially significant linguistic variation: The case of Palestinian Arabic. PhD dissertation, State Univ. of New York at Buffalo.</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/GroupScopeGroupScope2010-07-27T23:38:30Z<p>Mark Hasegawa-Johnson: Created page with 'The goal of this project is to develop GroupScope, an analytical tool that cuts the task of studying large dynamic groups down to manageable proportions, and to apply it to the s…'</p>
<hr />
<div>The goal of this project is to develop GroupScope, an analytical<br />
tool that cuts the task of studying large dynamic groups down to<br />
manageable proportions, and to apply it to the study of large dynamic<br />
groups.<br />
<br />
* [http://isle.illinois.edu/groupscope Group Home Page]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/ProjectsProjects2010-07-27T23:37:40Z<p>Mark Hasegawa-Johnson: /* Group dynamics and Discourse */</p>
<hr />
<div>Here are some projects that [[SST People]] are working on. For another view, see our [http://www.isle.uiuc.edu/pubs Publications].<br />
<br />
===Phonetics, Phonology, Semantics===<br />
<br />
; Prosody and Phonology in Automatic Speech Recognition (Landmark-Based Speech Recognition)<br />
: [[landmarks09F| Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/research/landmarks.html Landmark-Based Speech Recognition]<br />
: [http://www.isle.uiuc.edu/research/prosody_of_disfluency.html Prosody of Disfluency] <br />
<br />
; Very Large Corpus ASR/ Mixed-Units ASR<br />
: [[:Category:Fisher_Experiments|Large Vocabulary speech recognition using mixed units on fisher corpus]] <br />
<br />
; [[articulatory_feature_transcription|Articulatory Feature Transcription]]<br />
: [[Transcription_Guidelines|Transcription Guidelines]]<br />
: [[Phone-to-Feature_Mapping|Phone-to-Feature Mapping]]<br />
: [[Meeting_Summaries|Meeting Summaries]]<br />
: [[Resources|Resources]]<br />
<br />
=== Group dynamics and Discourse ===<br />
<br />
; GroupScope --- Dynamics of Medium-Sized Groups<br />
: [[GroupScope]]<br />
<br />
===Language Acquisition, Language Contact, Variability, and Disability===<br />
<br />
; Multi-Dialect Speech Recognition and Machine Translation for Qatari Broadcast TV<br />
: [[Multi Dialect Arabic]]<br />
<br />
; Cross-Language Transfer Learning<br />
: [[Linguistic Diversity References]]<br />
: [http://hlt.i2r.a-star.edu.sg/starchallenge Star Challenge competition]<br />
<br />
; Dynamics of Second Language Fluency<br />
: [http://serrano.ai.uiuc.edu/CRI/ Group Meeting Schedules and Slides]<br />
: [http://www.isle.uiuc.edu/research/fluency.html Description]<br />
: [[Dynamics of Second Language Fluency Data Description|Data Description]]<br />
<br />
; Universal Access<br />
: [[dysarthria09|Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/ua/index.html Description]<br />
: [http://www.isle.uiuc.edu/UASpeech UASpeech Database]<br />
<br />
===Multimodal Fusion, Speech and Non-Speech===<br />
<br />
; Audiovisual Event Detection and Visualization<br />
: [[compaudition09| Group Meeting Schedules and Slides]]<br />
: [[acoustic_events_papers| Papers]]<br />
: [[Visualization Experiments]]<br />
<br />
; Mobile Platform Acoustic-Frequency Environmental Tomography (was Dereverberation)<br />
: [[compaudition09| Group Meeting Schedules]]<br />
: [[Dereverberation Project| Project Status and Working Notes]]<br />
<br />
; Audiovisual Speech Recognition<br />
: [http://www.isle.uiuc.edu/research/audiovisual.html Description]<br />
: [http://www.isle.uiuc.edu/AVICAR/ AVICAR Database]<br />
<br />
<br />
==See also==<br />
[http://www.isle.uiuc.edu/pubs SST Publications] | [http://www.isle.uiuc.edu/sst.html SST Group]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Semitic_Language_ResourcesSemitic Language Resources2010-07-27T23:08:41Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>A wiki list being compiled as part of our [[Multi Dialect Arabic]] project.<br />
<br />
;On Line<br />
* [http://www.wikipedia.org Wikipedia, of course]<br />
* [http://www.ldc.upenn.edu LDC, of course]<br />
* [http://wals.info/ World Atlas of Language Structures]<br />
* [http://alrabiya.net/ Alrabiya.net Parallel Broadcast Text in MSA and Dialect]<br />
* [http://nlp.amharic.org/ Amharic NLP website]<br />
<br />
;References about Diglossia/Variation in Spoken Arabic<br />
* Abdel-Jawad, H. R. 1981. Lexical and phonological variation in spoken Arabic in Amman. PhD dissertation University of Pennsylvania.<br />
* Blanc. 1960. Stylistic variations in spoken Arabic, in Contribution to Arabic Linguistics (ed.) by Ferguson 1964. Cambridge, Mass. pp. 81-156.<br />
* Schmit, R. W. 1975. Sociostylistic variation in spoken Egyptian Arabic: Examination of the concept of diaglossia. PhD dissertation, Brown Univ.<br />
* Shorrab. 1981. Models of socially significant linguistic variation: The case of Palestinian Arabic. PhD dissertation, State Univ. of New York at Buffalo.</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Semitic_Language_ResourcesSemitic Language Resources2010-07-27T23:08:15Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>A wiki list being compiled as part of our [[Multi Dialect Arabic]] project.<br />
<br />
: On Line<br />
* [http://www.wikipedia.org Wikipedia, of course]<br />
* [http://www.ldc.upenn.edu LDC, of course]<br />
* [http://wals.info/ World Atlas of Language Structures]<br />
* [http://alrabiya.net/ Alrabiya.net Parallel Broadcast Text in MSA and Dialect]<br />
* [http://nlp.amharic.org/ Amharic NLP website]<br />
<br />
: References about Diglossia/Variation in Spoken Arabic<br />
* Abdel-Jawad, H. R. 1981. Lexical and phonological variation in spoken Arabic in Amman. PhD dissertation University of Pennsylvania.<br />
* Blanc. 1960. Stylistic variations in spoken Arabic, in Contribution to Arabic Linguistics (ed.) by Ferguson 1964. Cambridge, Mass. pp. 81-156.<br />
* Schmit, R. W. 1975. Sociostylistic variation in spoken Egyptian Arabic: Examination of the concept of diaglossia. PhD dissertation, Brown Univ.<br />
* Shorrab. 1981. Models of socially significant linguistic variation: The case of Palestinian Arabic. PhD dissertation, State Univ. of New York at Buffalo.</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Semitic_Language_ResourcesSemitic Language Resources2010-07-27T22:39:21Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>A wiki list being compiled as part of our [[Multi Dialect Arabic]] project.<br />
<br />
* [http://www.wikipedia.org Wikipedia, of course]<br />
* [http://www.ldc.upenn.edu LDC, of course]<br />
* [http://wals.info/ World Atlas of Language Structures]<br />
* [http://alrabiya.net/ Alrabiya.net Parallel Broadcast Text in MSA and Dialect]<br />
* [http://nlp.amharic.org/ Amharic NLP website]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Semitic_Language_ResourcesSemitic Language Resources2010-07-27T22:38:31Z<p>Mark Hasegawa-Johnson: Created page with '* [http://www.wikipedia.org Wikipedia, of course] * [http://www.ldc.upenn.edu LDC, of course] * [http://wals.info/ World Atlas of Language Structures] * [http://alrabiya.net/ Alr…'</p>
<hr />
<div>* [http://www.wikipedia.org Wikipedia, of course]<br />
* [http://www.ldc.upenn.edu LDC, of course]<br />
* [http://wals.info/ World Atlas of Language Structures]<br />
* [http://alrabiya.net/ Alrabiya.net Parallel Broadcast Text in MSA and Dialect]<br />
* [http://nlp.amharic.org/ Amharic NLP website]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-07-27T22:36:16Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Semitic Language Resources]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-07-27T22:34:04Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/postdoc.shtml Position Open in Qatar: Post-Doctoral Fellow]<br />
* [[Linguistic Diversity Resources]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-07-27T22:33:22Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/ Project Home Page]<br />
* [http://isle.illinois.edu/dialect/ Position Open: Post-Doctoral Fellow]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Multi_Dialect_ArabicMulti Dialect Arabic2010-07-27T22:32:59Z<p>Mark Hasegawa-Johnson: Created page with 'We are developing a new set of methods for integrated semantic-parse-based automatic speech recognition and machine translation between Qatari broadcast TV (including Modern Stan…'</p>
<hr />
<div>We are developing a new set of methods for integrated semantic-parse-based<br />
automatic speech recognition and machine translation between Qatari<br />
broadcast TV (including Modern Standard Arabic, Qatari Arabic as<br />
spoken on Qatari TV, and dialects from across the Arab world as heard<br />
on Qatari satellite television talk shows) and English.<br />
<br />
* [http://isle.illinois.edu/dialect/|Project Home Page]<br />
* [http://isle.illinois.edu/dialect/|Position Open: Post-Doctoral Fellow]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/ProjectsProjects2010-07-27T22:31:04Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>Here are some projects that [[SST People]] are working on. For another view, see our [http://www.isle.uiuc.edu/pubs Publications].<br />
<br />
===Phonetics, Phonology, Semantics===<br />
<br />
; Prosody and Phonology in Automatic Speech Recognition (Landmark-Based Speech Recognition)<br />
: [[landmarks09F| Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/research/landmarks.html Landmark-Based Speech Recognition]<br />
: [http://www.isle.uiuc.edu/research/prosody_of_disfluency.html Prosody of Disfluency] <br />
<br />
; Very Large Corpus ASR/ Mixed-Units ASR<br />
: [[:Category:Fisher_Experiments|Large Vocabulary speech recognition using mixed units on fisher corpus]] <br />
<br />
; [[articulatory_feature_transcription|Articulatory Feature Transcription]]<br />
: [[Transcription_Guidelines|Transcription Guidelines]]<br />
: [[Phone-to-Feature_Mapping|Phone-to-Feature Mapping]]<br />
: [[Meeting_Summaries|Meeting Summaries]]<br />
: [[Resources|Resources]]<br />
<br />
=== Group dynamics and Discourse ===<br />
<br />
; GroupScope --- Dynamics of Medium-Sized Groups<br />
: [[groupscope09| Group Meeting Schedules and Slides]]<br />
<br />
===Language Acquisition, Language Contact, Variability, and Disability===<br />
<br />
; Multi-Dialect Speech Recognition and Machine Translation for Qatari Broadcast TV<br />
: [[Multi Dialect Arabic]]<br />
<br />
; Cross-Language Transfer Learning<br />
: [[Linguistic Diversity References]]<br />
: [http://hlt.i2r.a-star.edu.sg/starchallenge Star Challenge competition]<br />
<br />
; Dynamics of Second Language Fluency<br />
: [http://serrano.ai.uiuc.edu/CRI/ Group Meeting Schedules and Slides]<br />
: [http://www.isle.uiuc.edu/research/fluency.html Description]<br />
: [[Dynamics of Second Language Fluency Data Description|Data Description]]<br />
<br />
; Universal Access<br />
: [[dysarthria09|Group Meeting Schedules and Slides]]<br />
: [http://www.isle.uiuc.edu/ua/index.html Description]<br />
: [http://www.isle.uiuc.edu/UASpeech UASpeech Database]<br />
<br />
===Multimodal Fusion, Speech and Non-Speech===<br />
<br />
; Audiovisual Event Detection and Visualization<br />
: [[compaudition09| Group Meeting Schedules and Slides]]<br />
: [[acoustic_events_papers| Papers]]<br />
: [[Visualization Experiments]]<br />
<br />
; Mobile Platform Acoustic-Frequency Environmental Tomography (was Dereverberation)<br />
: [[compaudition09| Group Meeting Schedules]]<br />
: [[Dereverberation Project| Project Status and Working Notes]]<br />
<br />
; Audiovisual Speech Recognition<br />
: [http://www.isle.uiuc.edu/research/audiovisual.html Description]<br />
: [http://www.isle.uiuc.edu/AVICAR/ AVICAR Database]<br />
<br />
<br />
==See also==<br />
[http://www.isle.uiuc.edu/pubs SST Publications] | [http://www.isle.uiuc.edu/sst.html SST Group]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Data_On_LineData On Line2010-07-26T15:23:40Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Databases Distributed by the Statistical Speech Technology Group==<br />
<br />
Our policy: everything we record is distributed for free. <br />
* Audiovisual speech is available, through secure ftp, to speech researchers at university or government labs. Contact username avicar at the domain name gmail.com for info.<br />
* Other types of data are posted free, on the web pages listed below.<br />
This page is intended to be the definitive list of data distributed by the SST group, because anybody in the group can edit it to add your own data.<br />
<br />
<table border=2><tr><br />
<tr><td>Audiovisual Speech</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/UASpeech UASPEECH]<br />
Train automatic recognizers of dysarthric speech</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/AVICAR AVICAR]<br />
100 Talkers, 4 Cameras, 8 Microphones, Moving Car</td></tr><br />
<br />
<tr><td>Dictionaries</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/dict ISLEX]<br />
International Speech Lexicon Project</td></tr><br />
<br />
<tr><td>Audio</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/roomresponses RIR]<br />
Measured Room Impulse Responses</td></tr><br />
<br />
<tr><td>MRI</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/mri VMRI:]<br />
5 Talkers, 10 Vowels, Axial and Coronal MR Image Stacks</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/physiology/coronal_micro Micro-MRI:] Voxel=59x59x49 microns, Human Cadaver Tongue</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/physiology/histology Micro-MRI:] Histology of the same Human Cadaver Tongue specimen</td></tr><br />
<br />
<tr><td>LDC Corpora</td></tr><br />
<tr><td></td><td><br />
[[:Category:Fisher Experiments|Fisher]]: Everything you want to know about the Fisher corpus</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/infograms Infograms:] Mutual information relative to phonetic landmarks (images)</td></tr><br />
<tr><td></td><td><br />
[[TIMIT]]: TIMIT files with unusual speech production phenomenon</td></tr><br />
<br />
</table></div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Data_On_LineData On Line2010-07-26T15:23:14Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Databases Distributed by the Statistical Speech Technology Group==<br />
<br />
Our policy: everything we record is distributed for free. <br />
* Audiovisual speech is available, through secure ftp, to speech researchers at university or government labs. Contact username avicar at the domain name gmail.com for info.<br />
* Other types of data are posted free, on the web pages listed below.<br />
This page is intended to be the definitive list of data distributed by the SST group, because anybody in the group can edit it to add your own data.<br />
<br />
<table border=2><tr><br />
<tr><td>Audiovisual Speech</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/UASpeech UASPEECH]<br />
Train automatic recognizers of dysarthric speech</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/AVICAR AVICAR]<br />
100 Talkers, 4 Cameras, 8 Microphones, Moving Car</td></tr><br />
<br />
<tr><td>Dictionaries</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/dict ISLEX]<br />
International Speech Lexicon Project</td></tr><br />
<br />
<tr><td>Audio</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/roomresponses RIR]<br />
Measured Room Impulse Responses</td></tr><br />
<br />
<tr><td>MRI</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/mri VMRI:]<br />
5 Talkers, 10 Vowels, Axial and Coronal MR Image Stacks</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/physiology/coronal_micro Micro-MRI:] Voxel=59x59x49 microns, Human Cadaver Tongue</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/physiology/histology Micro-MRI:] Histology of the same Human Cadaver Tongue specimen</td></tr><br />
<br />
<tr><td>LDC Corpora</td></tr><br />
<tr><td></td><td><br />
[[:Category:Fisher Experiments|Fisher]]: Everything you want to know about the Fisher corpus</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/infograms Infograms:] Mutual information relative to phonetic landmarks (images)</td></tr><br />
<tr><td></td><td><br />
[[TIMIT]]: TIMIT files with unusual speech production phenomenon</td></tr><br />
<br />
</table></div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Data_On_LineData On Line2010-07-26T15:22:52Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Databases Distributed by the Statistical Speech Technology Group==<br />
<br />
Our policy: everything we record is distributed for free. <br />
* Audiovisual speech is available, through secure ftp, to speech researchers at university or government labs. Contact username avicar at the domain name gmail.com for info.<br />
* Other types of data are posted free, on the web pages listed below.<br />
This page is intended to be the definitive list of data distributed by the SST group, because anybody in the group can edit it to add your own data. The page [http://www.isle.uiuc.edu/data/index.html] is a sort of archival, spider-indexable copy of this one.<br />
<br />
<table border=2><tr><br />
<tr><td>Audiovisual Speech</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/UASpeech UASPEECH]<br />
Train automatic recognizers of dysarthric speech</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/AVICAR AVICAR]<br />
100 Talkers, 4 Cameras, 8 Microphones, Moving Car</td></tr><br />
<br />
<tr><td>Dictionaries</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/dict ISLEX]<br />
International Speech Lexicon Project</td></tr><br />
<br />
<tr><td>Audio</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/roomresponses RIR]<br />
Measured Room Impulse Responses</td></tr><br />
<br />
<tr><td>MRI</td></tr><br />
<tr><td></td><td>[http://isle.uiuc.edu/sst/data/mri VMRI:]<br />
5 Talkers, 10 Vowels, Axial and Coronal MR Image Stacks</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/physiology/coronal_micro Micro-MRI:] Voxel=59x59x49 microns, Human Cadaver Tongue</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/physiology/histology Micro-MRI:] Histology of the same Human Cadaver Tongue specimen</td></tr><br />
<br />
<tr><td>LDC Corpora</td></tr><br />
<tr><td></td><td><br />
[[:Category:Fisher Experiments|Fisher]]: Everything you want to know about the Fisher corpus</td></tr><br />
<tr><td></td><td><br />
[http://isle.uiuc.edu/sst/research/infograms Infograms:] Mutual information relative to phonetic landmarks (images)</td></tr><br />
<tr><td></td><td><br />
[[TIMIT]]: TIMIT files with unusual speech production phenomenon</td></tr><br />
<br />
</table></div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:17:48Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] <br />
|<br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
| rowspan="3"| <br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:15:18Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] <br />
|<br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
| rowspan="3"| <br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.isr.umd.edu/labs/SCL Maryland ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:14:02Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] <br />
|<br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
|<br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.isr.umd.edu/labs/SCL Maryland ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:13:05Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] <br />
| rowspan="3"| <br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
|<br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.isr.umd.edu/labs/SCL Maryland ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:10:39Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] <br />
| rowspan="3"| <br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
| rowspan="3"| <br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.isr.umd.edu/labs/SCL Maryland ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:09:03Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] <br />
|-<br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
| rowspan="3"| <br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.isr.umd.edu/labs/SCL Maryland ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Main_PageMain Page2010-07-22T15:08:26Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>__NOEDITSECTION__<br />
__NOTOC__<br />
<!-- If you want a special news section use this below<br />
<br />
{| id="mp-tfp" <br />
| class="mp-SpecialMessage-table" |<br />
{| cellpadding="2" cellspacing="5" style="vertical-align:top; background:#faf5ff; color:#000; width:100%"<br />
! <h2 class="mp-SpecialMessage-heading" >Upcoming Speech Prosody Conference 2010</h2><br />
|-<br />
| style="color:#000;" | <span class="plainlinks">[http://www.speechprosody2010.illinois.edu http://mickey.ifp.uiuc.edu/speechWiki/images/thumb/c/c9/SpeechProsodyBanner01.jpg/500px-SpeechProsodyBanner01.jpg]</span><br />
|}<br />
|}<br />
<br />
--><br />
<br />
= Welcome to Statistical Speech Technology Wiki! =<br />
<br />
{| class="mp-cat-table" cellpadding="2" cellspacing="5"<br />
! width="50%" | <h2 class="mp-cat-heading" >[[file:Nuvola_filesystems_folder_home.svg|64px|link=]] Our group and our work </h2><br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_miscellaneous.svg|64px|link=]] Educational Opportunities</h2><br />
|-valign="top"<br />
| class="mp-body"| <br />
[[SST People | People (and their Photos)]] |<br />
[http://www.isle.illinois.edu/sst/ Group Home Page] |<br />
[http://www.isle.illinois.edu/sst/pubs Publications] | <br />
[[Current events]] | <br />
[[Software]] | <br />
[[Computer Resources]] | <br />
[[Data On Line]] | <br />
[[Working Papers]] | <br />
[http://lsp.lang.uiuc.edu/ LSP] |<br />
[http://courses.ece.uiuc.edu/ece537/ ECE 537] |<br />
[http://www.isle.uiuc.edu/courses/tsinghua/index.html Landmarks] |<br />
[http://www.isle.uiuc.edu/courses/minicourse/2009/index.html Tools] |<br />
[http://www.isle.uiuc.edu/courses/htk/index.html HTK] |<br />
[http://www.isle.uiuc.edu/courses/index.html Other]<br />
|-<br />
! <h2 class="mp-cat-heading"> [[file:Nuvola_apps_edu_science.png|64px|link=]] Our Research Projects</h2><br />
! <h2 class="mp-cat-heading"> [[file:Globe_of_letters.svg|64px|link=]] Our Collaborators</h2><br />
|-valign="top"<br />
| style="color:#000;" | <br />
[[Projects | Current Grants and Projects]] |<br />
[[Landmark-Based and Prosody-Dependent Speech Recognition]]<br />
| rowspan="3"| <br />
====University of Illinois====<br />
[http://www.isle.uiuc.edu ISLE] |<br />
[http://l2r.cs.uiuc.edu/~cogcomp/uiuc_nlp/ NLP] |<br />
[http://www.beckman.uiuc.edu Beckman] |<br />
[http://www.ece.uiuc.edu ECE] |<br />
[http://www.cs.uiuc.edu CS] |<br />
[http://www.linguistics.uiuc.edu Linguistics] |<br />
[http://www.shs.uiuc.edu SHS] |<br />
[http://prosody.beckman.uiuc.edu Prosody] |<br />
[http://compling.ai.uiuc.edu Comp Ling] | <br />
[http://www.disability.uiuc.edu DRES] |<br />
[http://www.ifp.uiuc.edu IFP] |<br />
[http://hear.ai.uiuc.edu/ HSR ] |<br />
[http://wiki.engr.uiuc.edu/display/3dmultimedia/Home 4D Multimedia Initiative] |<br />
[https://wiki.cites.uiuc.edu/wiki/display/ahshealth/Home Health and Wellness Initiative]<br />
<br />
====Planet Earth====<br />
[http://dsp.rice.edu/muri31 Rice] |<br />
[http://ttic.uchicago.edu/~klivescu/ TTI] |<br />
[http://www.clsp.jhu.edu/ws2006/ JHU] |<br />
[http://ssli.ee.washington.edu Washington] |<br />
[http://www.ar.media.kyoto-u.ac.jp/ Kyoto ] |<br />
[http://www.isr.umd.edu/labs/SCL Maryland ] |<br />
[http://www.haskins.yale.edu/tada_download/index.html Haskins ] |<br />
[http://www.ee.ucla.edu/~spapl UCLA ]<br />
|-<br />
! <h2 class="mp-cat-heading">[[file:WLM_logo-2.svg|64px|link=]] Upcoming Conferences</h2><br />
!<br />
|-<br />
| <br />
[http://www.interspeech2010.org Interspeech 2010 ] | [http://www.icassp2011.com ICASSP 2011] |<br />
[[Conferences | Speech Conference Proceedings]]<br />
|}</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/SST_PeopleSST People2010-07-22T15:05:06Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Our Group ==<br />
<br />
[[Image:Fall2009GroupPhoto.jpg|700px|thumb|center| SST Group photo, fall 2009]]<br />
<br />
<br />
<gallery perrow="4" style="width:100%;" widths="200px" caption="More photos of us"><br />
Image:Bowon_defense2.jpg|Bowon Lee's Thesis Defense<br />
Image:Rio_five2.jpg|Speech Prosody 2008<br />
Image:London_2009_320_small.jpg|Interspeech 2009<br />
Image:London_2009_366_small.jpg|Interspeech 2009<br />
</gallery><br />
<br />
<gallery perrow="4" style="width:100%;" widths="200px" caption="ASR-Prosody group in Kickapoo park, IL, Summer 2010"><br />
Image:SarahWaterfall.jpg<br />
Image:SarahMarkArthur.jpg<br />
Image:Prosody-ASR Group post-canoetrip.jpg<br />
Image:PeaceOutforASR.jpg<br />
Image:MarkH-J.jpg<br />
Image:MarkArthur.jpg<br />
Image:JuiTing.jpg<br />
Image:Jose.jpg<br />
Image:Jennifer.jpg<br />
Image:ErinJui-Ting.jpg<br />
Image:Erin.jpg<br />
Image:AfterCanoeing.jpg<br />
Image:AfterCanoeing.jpg<br />
Image:ProsodySwans.jpg<br />
</gallery><br />
<br />
<br />
<br />
==Our Group Members==<br />
<br />
E-mail addresses are available at the [http://illinois.edu/ows/PH Illinois PH server]<br />
<br />
<div style="column-count:2;-moz-column-count:2;-webkit-column-count:2"><br />
* [http://zx81.isl.uiuc.edu/camilleg/ Camille Goudeseune]<br />
* [[Image:Mark2.jpg]] [http://www.isle.uiuc.edu/~hasegawa Mark Hasegawa-Johnson]<br />
* [[image:huchi.jpg|100px]] [http://www.facebook.com/home.php#/profile.php?id=705278083&ref=profile Chi Hu]<br />
* [[Image:Juiting.jpg]] Jui-Ting Huang<br />
* Po-Sen Huang<br />
* [[Image:ArthurMugSmall.jpg|100px]] [http://www.isle.uiuc.edu/~akantor Arthur Kantor]<br />
* [http://heejin.fayoly.net/ Heejin Kim]<br />
* [[Image:Tahn small.jpg]] Kyungtae Kim<br />
* [[Image:Lkim9.jpg]] [http://www.isle.uiuc.edu/~lkim9 Lae-Hoon Kim]<br />
* [[Image:Sarah.jpg]] [http://www.isle.uiuc.edu/~sborys Sarah King]<br />
* [[Image:bryce_small.jpg|100px]] [mailto:lobdellb@gmail.com Bryce Lobdell]<br />
* [[Image:Yoonsook.jpg]] Yoonsook Mo<br />
* [http://www.eee.metu.edu.tr/~yozbek/ Yucel Ozbek]<br />
* [[Image:hsharma.jpg|75px]] [https://netfiles.uiuc.edu/hsharma/www/index.html Harsh Vardhan Sharma]<br />
* Jeremy Tidemann<br />
* [http://www.facebook.com/people/Su-Youn_Yoon/635390333 Su-Youn Yoon]<br />
* [[Image:Xiaodan.jpg]] [http://netfiles.uiuc.edu/xzhuang2/www Xiaodan Zhuang]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-06-22T17:10:01Z<p>Mark Hasegawa-Johnson: </p>
<hr />
<div>==Landmark-Based and Prosody-Dependent Speech Recognition, Spring 2010==<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 15;<br />
:12:30 - 2:00<br />
:Third summer meeting<br />
: continue discussing papers from June 8th meeting<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
:* [http://speechprosody2010.illinois.edu/papers/100580.pdf A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping]<br />
:* [http://speechprosody2010.illinois.edu/papers/100582.pdf A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1024.pdf Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1025.pdf Contextual Information Improves OOV Detection in Speech]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1023.pdf Formatting Time-Aligned ASR Transcripts for Readability]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1005.pdf Appropriately Handled Prosodic Breaks Help PCFG Parsing]<br />
:* [http://aclweb.org/anthology-new/N/N10/N10-1109.pdf Classification of Prosodic Events using Quantized Contour Modeling]<br />
:* Subword Variation in Text Message Classification<br />
:* [http://speechprosody2010.illinois.edu/papers/100113.pdf Cross-genre training for automatic prosody classification (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100892.pdf Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100067.pdf Automatic duration-related salience detection in Brazilian Portuguese read and spontaneous speech (Speech Prosody)]<br />
:* [http://speechprosody2010.illinois.edu/papers/100445.pdf The effect of global F0 contour shape on the perception of tonal timing contrasts in American English intonation (Speech Prosody)]<br />
:* [[Media:Munro-Manning NAACL10.pdf|Subword Variation in Text Message Classification]]<br />
:* [http://www.magic.ubc.ca/artisynth artisynth]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-06-07T21:22:41Z<p>Mark Hasegawa-Johnson: /* June 2010 */</p>
<hr />
<div>==Landmark-Based and Prosody-Dependent Speech Recognition, Spring 2010==<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
: A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping [[http://speechprosody2010.illinois.edu/papers/100580.pdf]]<br />
: A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition [[http://speechprosody2010.illinois.edu/papers/100582.pdf]]<br />
: Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription [[http://naaclhlt2010.isi.edu/full-program.html#speech]]<br />
: Contextual Information Improves OOV Detection in Speech [[http://naaclhlt2010.isi.edu/full-program.html#speech]]<br />
: Formatting Time-Aligned ASR Transcripts for Readability [[http://naaclhlt2010.isi.edu/full-program.html#speech]]<br />
: Appropriately Handled Prosodic Breaks Help PCFG Parsing [[http://naaclhlt2010.isi.edu/full-program.html#parsing-i]]<br />
: Classification of Prosodic Events using Quantized Contour Modeling [[http://naaclhlt2010.isi.edu/full-program.html#ml-short]]<br />
: Subword Variation in Text Message Classification<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnsonhttp://mickey.ifp.illinois.edu/speechWiki/index.php/Landmark-Based_and_Prosody-Dependent_Speech_RecognitionLandmark-Based and Prosody-Dependent Speech Recognition2010-06-07T20:44:47Z<p>Mark Hasegawa-Johnson: /* June 2010 */</p>
<hr />
<div>==Landmark-Based and Prosody-Dependent Speech Recognition, Spring 2010==<br />
<br />
===June 2010===<br />
<br />
; Tuesday June 8;<br />
: 12:30 - 2:00<br />
: Second Summer Meeting<br />
: Paper(s) to be discussed:<br />
: A Novel Feature Extraction for Neural-based Modes in Acoustic-Articulatory Inversion Mapping [[http://speechprosody2010.illinois.edu/papers/100580.pdf]]<br />
: A New Bidirectional Neural Network Model for the Acoustic-Articulatory Inversion Mapping For Speech Recognition [[http://speechprosody2010.illinois.edu/papers/100582.pdf]]<br />
: Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription [[http://naaclhlt2010.isi.edu/full-program.html#speech]]<br />
: Contextual Information Improves OOV Detection in Speech [[http://naaclhlt2010.isi.edu/full-program.html#speech]]<br />
: Formatting Time-Aligned ASR Transcripts for Readability [[http://naaclhlt2010.isi.edu/full-program.html#speech]]<br />
: Appropriately Handled Prosodic Breaks Help PCFG Parsing [[http://naaclhlt2010.isi.edu/full-program.html#parsing-i]]<br />
: Classification of Prosodic Events using Quantized Contour Modeling [[http://naaclhlt2010.isi.edu/full-program.html#ml-short]]<br />
<br />
===May 2010===<br />
<br />
; Tuesday May 25;<br />
: 12:30 - 2:00<br />
: First Summer Meeting<br />
: Paper(s) to be discussed:<br />
<br />
; Tuesday May 11, <br />
: 8:00-6:30, 2169 BI<br />
: [http://speechprosody2010.illinois.edu Speech Prosody]<br />
<br />
; Tuesday May 4, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang, Jennifer Cole<br />
: Speech Prosody Practice Talks<br />
<br />
===April 2010===<br />
<br />
; Tuesday April 27, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo, David Harwath<br />
: Speech Prosody Practice Talks<br />
<br />
; Tuesday April 20, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://asa.aip.org/baltimore/baltimore.html ASA]?<br />
<br />
; Tuesday April 13, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday April 6, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===March 2010===<br />
<br />
; Tuesday March 30, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
; Tuesday March 23, <br />
: 12:30-2:00, 2169 BI<br />
: Spring Break<br />
<br />
; Tuesday March 16, <br />
: 12:30-2:00, 2169 BI<br />
: Skip meeting because of [http://www.icassp2010.com ICASSP]?<br />
<br />
; Tuesday March 9, <br />
: 12:30-2:00, 2169 BI<br />
: Arthur presents<br />
: (moved to the waiting list) Discussion on two papars about unsupervised and supervised prosodic event detection. ([http://mickey.ifp.uiuc.edu/speechWiki/images/1/1d/Levow_IS09.pdf Levow's paper] and [http://mickey.ifp.uiuc.edu/speechWiki/images/e/ee/AnanthakrishnanTASLP2008.pdf Ananthakrishnan et al.])<br />
<br />
; Tuesday March 2, <br />
: 12:30-2:00, 2169 BI<br />
: open<br />
<br />
===February 2010===<br />
<br />
; Tuesday February 23, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Gesture-based lexicon for speech recognition<br />
<br />
; Tuesday February 16, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt and Jui-Ting Huang<br />
: Automatic prosody detection<br />
<br />
; Tuesday February 9, <br />
: 12:30-2:00, 2169 BI<br />
: Xiaodan Zhuang<br />
: Audiovisual speech synthesis<br />
<br />
; Tuesday February 2, <br />
: 12:30-2:00, 2169 BI<br />
: Dayna <br />
: Phonetic correlates of focus scope<br />
<br />
===January 2010===<br />
<br />
; Tuesday January 26, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Open discussion<br />
: What are the [http://macserver.haskins.yale.edu/tada_download/index.html TADA] gestures? Gestural scores<br />
: Some sketch of Canonical Gesture Scores in TADA: [[Media:before_gs.jpg|"before"]], [[Media:about_gs.jpg|"about"]], [[Media:brush_gs.jpg|"brush"]], [[Media:companions_gs.jpg|"companions"]],<br />
<br />
; Tuesday January 19, 2010, <br />
: 12:30-2:00, 2169 BI<br />
: Planning meeting for spring semester<br />
<br />
==Fall 2009==<br />
<br />
; Tuesday December 8, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Tim Mahrt<br />
: Automatic P-score and B-score labeling using HMMs<br />
<br />
; Tuesday December 1, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Yoonsook Mo<br />
: Speaker-dependent vs. speaker-independent models of prosody<br />
: Boundary detection with vs without pause<br />
<br />
; Tuesday November 11, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jui-Ting Huang and Po-Sen Huang<br />
: Variable-parameter HMM indexed by P-score (prominence score)<br />
<br />
; Tuesday October 20, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Chi Hu<br />
: Finite State ASR Dictionary using Gesture Pattern Vectors as Units<br />
<br />
; Tuesday October 13, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Alina Khasanova<br />
: Stop Consonant Reduction Phenomena<br />
<br />
; Tuesday October 6, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Jennifer Cole<br />
: presents Daniel Hirst's tutorial, [http://interspeech2009.org/tutorials/t-1.php Prosody Modeling and Synthesis], from Interspeech<br />
<br />
; Tuesday September 30, 2009, <br />
: 12:30-2:00, 2169 BI<br />
: Mark Hasegawa-Johnson<br />
: presents Tokuda & Zen tutorial, [http://interspeech2009.org/tutorials/t-7.php HMM-Based Speech Synthesis], from Interspeech<br />
<br />
==Summer 2009==<br />
<br />
The landmark-based speech recognition group will meet during Summer 2009 on roughly alternate Thursdays, from 10:00-11:30 AM, in Beckman 2369.<br />
<br />
; August 6, 2009<br />
: Sarah will present her work with auditory modeling.<br />
<br />
; July 23, 2009<br />
: Chi will lead a discussion of three papers on finite state transducers to model pronunciation variation:<br />
: Timothy J. Hazen, I. Lee Hetherington, Han Shu, and Karen Livescu, 2002. PRONUNCIATION MODELING USING (Priority)<br />
: A FINITE-STATE TRANSDUCER REPRESENTATION. http://groups.csail.mit.edu/sls//publications/2002/hazen-pmla.pdf<br />
: Han Shu and I. Lee Hetherington, 2002. EM TRAINING OF FINITE-STATE TRANSDUCERS<br />
: AND ITS APPLICATION TO PRONUNCIATION MODELING. http://groups.csail.mit.edu/sls//publications/2002/shu-icslp.pdf<br />
: I. Lee Hetherington, 2001. An Efficient Implementation of Phonological Rules<br />
: using Finite-State Transducers. http://groups.csail.mit.edu/sls/publications/2001/ilh-preprint.pdf<br />
: Chi will present her work with Xiaodan on word recognition from tract variables using Vikram's data(If time is enough)<br />
<br />
; July 16, 2009<br />
: Alina will discuss her current work on the frequency of vowel co-occurrence patterns in the English CELEX lexicon. <br />
: Dave will lead the discussion of Tilsen & Johnson's JASA paper. The 2008 CLS paper covers the same material but is lighter on technical detail and directed to a linguistics reader. The 2009 CogSci paper will not be discussed but is shared here.<br />
<br />
: Tilsen, S. & Johnson, K. (2008). Low-frequency Fourier analysis of speech rhythm. Journal of the Acoustical Society of America, 124:2, pp. EL34-39.<br />
: Tilsen, S. (2008). Relations between speech rhythm and segmental deletion. Paper presented at the 44th annual meeting of the Chicago Linguistic Society.<br />
: Tilsen, S. (2009). Multitimescale dynamical interactions between speech rhythm and gesture. Cognitive Science, 33, 839-879.<br />
: These articles can be found at http://linguistics.berkeley.edu/~stilsen/CV.html<br />
<br />
; July 2, 2009 <br />
: Alina discussed the design of her EMA study on plosive release<br />
<br />
; June 18, 2009<br />
: Discuss plans for summer<br />
<br />
==Spring 2009==<br />
<br />
; May 7-8, 2009<br />
: Multi-University Landmark-Based Speech Recognition Group Meeting<br />
: University of Maryland<br />
<br />
; April 30<br />
: Practice talks for Illinois Speech Day, ASA<br />
: Yoonsook Mo, Arthur Kantor, Chi Hu, Jui-Ting Huang, Sarah Borys<br />
<br />
; April 23<br />
: A nice intro to kernel methods is [http://mickey.ifp.uiuc.edu/speech/akantor/ece513/papers/P%e9rez-Cruz2004Kernel%20methods%20and%20their%20potential%20use%20in%20signal%20processing.pdf Kernel Methods and their potential use in signal processing, F. Perez-Cruz, O. Bousquet, IEEE SIGNAL PROCESSING MAGAZINE MAY 2004] --[[User:Arthur|Arthur]]<br />
; April 16<br />
: Discussion of Interspeech Papers<br />
<br />
; April 9<br />
<br />
; April 2<br />
<br />
; March 26 <br />
: Spring break<br />
<br />
; March 19<br />
: Five-minute presentations of student research; Bob McMurray will be here<br />
<br />
; March 12<br />
: Practice of the Universal Access Open House demo<br />
: Heejin Kim, Mark Hasegawa-Johnson, Sarah Borys, Sujeeth Bhardwoy<br />
<br />
; March 5, 2009<br />
: [http://www.isle.uiuc.edu/papers/Tanenhaus08.pdf Language Processing in the Natural World], Michael T. Tanenhaus and Sarah Brown-Schmidt<br />
<br />
; February 26, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/MULTIIR-0226.pdf Cross-Lingual Recognition and Sound Pattern Retrieval], Jui-Ting Huang and Xiaodan Zhuang<br />
<br />
; February 12, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Khasanova2009Feb12.ppt Automatic Burst Location], Alina Khasanova<br />
<br />
; February 19, 2009<br />
: Discussion of Kuperman et al. 2008 (JASA v. 124.6) and Margaret Fleck's attempts to replicate results with Buckeye<br />
<br />
; February 5, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Mo2009Feb05.pdf F0 Peak and Formant Values as Cues for Prominence], Yoonsook Mo<br />
<br />
; January 29, 2009<br />
: [http://www.isle.uiuc.edu/slides/2009/Borys2009Jan29.pdf Landmark-Based Speech Recognition Using SVM/HMM Hybrids], Sarah Borys<br />
<br />
; January 22, 2009: Planning meeting<br />
<br />
==Fall 2008==<br />
<br />
Faculty and students from the University of Maryland, Boston University, the University of Illinois, UCLA, and USC met in Urbana on September 12, 2008 to present new results in landmark-based speech recognition.<br />
<br />
; [http://www.isle.uiuc.edu/slides/2008/Kantor2008Sep12.pdf Insights Into Pronunciation Modeling and ASR Using Mixed Unit Pronunciation Models]<br />
: Arthur Kantor<br />
<br />
[[Category:Events]]</div>Mark Hasegawa-Johnson