Computer Resources

From SpeechWiki

(Difference between revisions)
Jump to: navigation, search
(→LVCSR at Illinois Computer Resources)
(→Applications)
Line 18: Line 18:
==Applications==
==Applications==
-
* Hidden Markov Models:  
+
 
-
** HTK (Cambridge): fluffy0/programs/htk-3.3
+
* Acoustic model training:  
-
** DCD (ATT): nibbler0/speech_apps/dcd-2.0
+
** [http://www.htk.eng.cam.ac.uk HTK] hidden Markov modeling toolkit: ifp-32-1/hasegawa/programs/htk-3.4
-
* Dynamic Bayesian Nets/Graphical Models: nibbler0/speech_apps/GMTK
+
** [http://ssli.ee.washington.edu/~bilmes/gmtk/ GMTK] Dynamic Bayesian Nets/Graphical Models: nibbler0/speech_apps/GMTK
-
* Language Models: fluffy0/programs/srilm
+
** [http://cmusphinx.sourceforge.net Sphinx] speech recognizer
-
* Finite State Machines:
+
 
-
** FSM (ATT): fluffy0/programs/fsm-4.0
+
* Decoding:
-
** FST (MIT): fluffy0/programs/fst-1.0-RC1 (MIT)
+
** [http://julius.sourceforge.jp/en_index.php Julius] LVCSR decoder
-
** OpenFST : fluffy0/programs/OpenFst/
+
** [http://www.research.att.com/~fsmtools/dcd/ AT&T DCD] LVCSR decoder - nibbler0/speech_apps/dcd-2.0
-
* Support Vector Machines:
+
 
-
** SVMLIB (NJTU): fluffy0/programs/svmlib
+
* Language model training:
-
** svm_light (Joachims): fluffy0/programs/svm_light
+
** [http://www.speech.sri.com/projects/srilm/ SRILM] Big N-gram counts and backoff, lattices: fluffy0/programs/srilm
-
** PVTK (UIUC): mickey0/SVM/PVTK
+
** [http://www.research.att.com/~fsmtools/fsm/ AT&T FSM Library]: fluffy0/programs/fsm-4.0
-
* Neural Nets
+
** [http://www.openfst.org OpenFST]: fluffy0/programs/OpenFst/
-
** quicknet (ICSI): mickey0/quicknet
+
 
 +
* Scoring
 +
** [http://www.nist.gov/speech/tools/ NIST Speech Tools]: ifp-32-1/hasegawa/programs
 +
 
 +
* Support Vector Machines and Neural Networks
 +
** [http://www.csie.ntu.edu.tw/~cjlin/libsvm/ libSVMLIB]: fluffy0/programs/svmlib
 +
** [http://www.cs.cornell.edu/people/tj/svm_light/ svm_light]: fluffy0/programs/svm_light
 +
** [http://www.icsi.berkeley.edu/Speech/icsi-speech-tools.html quicknet]: mickey0/quicknet
 +
 
* Spectrograms and Waveform Viewing
* Spectrograms and Waveform Viewing
** XKL (MIT): nibbler0/speech_apps/xkl-2.3.1
** XKL (MIT): nibbler0/speech_apps/xkl-2.3.1
** ESPS (Entropic Systems, now Microsoft)
** ESPS (Entropic Systems, now Microsoft)
** Praat
** Praat
-
* Speech Data File Formats:
 
-
** SPHERE (NIST): fluffy0/programs/sphere
 
-
** sox (linux): /usr/bin/sox
 
-
** HCopy (Cambridge): see HTK
 
==Backups==
==Backups==

Revision as of 00:53, 16 June 2008

LVCSR at Illinois Computer Resources

  • Data:
    • We distribute the AVICAR corpus via sftp to interested researchers
    • We distribute the UASPEECH corpus via sftp to interested researchers
    • We are members of LDC. Most LDC data is organized as described in the Data Organization README. Some useful slices of LDC data that have not been moved to ifp-32-2 include:
      • /workspace/fluffy1/12hour - 12 hours extracted from Switchboard 1, with SPHERE and WAV audio, MFCCs, transcriptions.
      • /workspace/fluffy1/{train-ws96,train-ws97,misc-ws97} - The ICSI phonetically transcribed Switchboard-1 extracts
      • /workspace/fletcher1/bdc - The Boston Directions Corpus, two speakers have prosodic transcriptions, others don't
      • /workspace/nibbler0/data/ylzheng/WS04/DATA - Tsinghua Wu-accented Mandarin (MFCC and FMT only, no waveforms)
  • Time-aligned Switchboard Disfluency corpus
    • mickey0/sw_disTime-0.9.9 - merged from the original Switchboard time transcription and the Treebank-3 disfluency transcription (TextGrid included)
    • mickey0/sw_disTime-1.0.0 (TextGrid NOT included)

Applications

  • Acoustic model training:
    • HTK hidden Markov modeling toolkit: ifp-32-1/hasegawa/programs/htk-3.4
    • GMTK Dynamic Bayesian Nets/Graphical Models: nibbler0/speech_apps/GMTK
    • Sphinx speech recognizer
  • Decoding:
    • Julius LVCSR decoder
    • AT&T DCD LVCSR decoder - nibbler0/speech_apps/dcd-2.0
  • Language model training:
    • SRILM Big N-gram counts and backoff, lattices: fluffy0/programs/srilm
    • AT&T FSM Library: fluffy0/programs/fsm-4.0
    • OpenFST: fluffy0/programs/OpenFst/
  • Support Vector Machines and Neural Networks
  • Spectrograms and Waveform Viewing
    • XKL (MIT): nibbler0/speech_apps/xkl-2.3.1
    • ESPS (Entropic Systems, now Microsoft)
    • Praat

Backups

If you have personal working directories that should be regularly backed up, outside of your own home directory, list them here.

  • Art
    • mickey0/akantor
    • rizzo1/akantor is itself a backup of svn because it cannot be backed up in the normal way.
  • Sarah
    • nibbler0/data
    • rizzo0/sborys
    • spot1/sborys
    • tico0/sborys
  • Bowon
    • mickey1/AVICAR_AUDIO
    • mickey1/AVICAR_DATA
    • mickey1/AVICAR_DIST
    • mickey1/AVICAR_DIST_OLD
    • rizzo1/bowonlee
    • mickey0/bowonlee
  • Mital
    • mickey0/magandhi
  • Xiaodan
    • spot1/xzhuang2/newbaseline
    • spot1/xzhuang2/workshop
    • c1-15/hasegawa/xzhuang2*
    • /workspace/tico0/AED/
  • Rajiv
    • scratch/rreddy
Retrieved from "http://mickey.ifp.illinois.edu/speechWiki/index.php/Computer_Resources"
Personal tools