:Units Paper

From SpeechWiki

(Difference between revisions)
Jump to: navigation, search
Line 55: Line 55:
=== with LM_PENALTY=0 ===
=== with LM_PENALTY=0 ===
-
DETAILED OVERALL REPORT FOR THE SYSTEM: test/config16/test0/accuracy/out.nosil.trn
+
DETAILED OVERALL REPORT FOR THE SYSTEM: test/config16/test0/accuracy/out.nosil.trn
-
 
+
-
SENTENCE RECOGNITION PERFORMANCE
+
SENTENCE RECOGNITION PERFORMANCE
-
 
+
  sentences                                        500
  sentences                                        500
  with errors                            89.2%  ( 446)
  with errors                            89.2%  ( 446)
-
 
+
   with substitions                      72.4%  ( 362)
   with substitions                      72.4%  ( 362)
   with deletions                        26.2%  ( 131)
   with deletions                        26.2%  ( 131)
   with insertions                      74.4%  ( 372)
   with insertions                      74.4%  ( 372)
-
 
+
-
 
+
-
WORD RECOGNITION PERFORMANCE
+
WORD RECOGNITION PERFORMANCE
-
 
+
-
Percent Total Error      =  99.1%  (5107)
+
Percent Total Error      =  99.1%  (5107)
-
 
+
-
Percent Correct          =  28.6%  (1476)
+
Percent Correct          =  28.6%  (1476)
-
 
+
-
Percent Substitution      =  66.2%  (3411)
+
Percent Substitution      =  66.2%  (3411)
-
Percent Deletions        =    5.1%  ( 265)
+
Percent Deletions        =    5.1%  ( 265)
-
Percent Insertions        =  27.8%  (1431)
+
Percent Insertions        =  27.8%  (1431)
-
Percent Word Accuracy    =    0.9%
+
Percent Word Accuracy    =    0.9%
-
 
+
-
 
+
-
Ref. words                =          (5152)
+
Ref. words                =          (5152)
-
Hyp. words                =          (6318)
+
Hyp. words                =          (6318)
-
Aligned words            =          (6583)
+
Aligned words            =          (6583)
-
 
+
-
CONFUSION PAIRS                  Total                (2790)
+
CONFUSION PAIRS                  Total                (2790)
                                 With >=  1 occurances (2790)
                                 With >=  1 occurances (2790)
=== with LM_PENALTY=-1 ===
=== with LM_PENALTY=-1 ===
-
test2kUtt/config16Disaster/test0/accuracy/out.nosil.trn.dtl  
+
test2kUtt/config16Disaster/test0/accuracy/out.nosil.trn.dtl  
-
DETAILED OVERALL REPORT FOR THE SYSTEM: test2kUtt/config16/test0/accuracy/out.nosil.trn
+
DETAILED OVERALL REPORT FOR THE SYSTEM: test2kUtt/config16/test0/accuracy/out.nosil.trn
-
 
+
-
SENTENCE RECOGNITION PERFORMANCE
+
SENTENCE RECOGNITION PERFORMANCE
-
 
+
   
-
  sentences                                        500
+
  sentences                                        500
-
with errors                            88.2%  ( 441)
+
  with errors                            88.2%  ( 441)
-
 
+
   with substitions                      72.8%  ( 364)
   with substitions                      72.8%  ( 364)
   with deletions                        32.8%  ( 164)
   with deletions                        32.8%  ( 164)
   with insertions                      68.6%  ( 343)
   with insertions                      68.6%  ( 343)
-
 
+
-
 
+
-
WORD RECOGNITION PERFORMANCE
+
WORD RECOGNITION PERFORMANCE
-
 
+
-
Percent Total Error      =  94.6%  (4857)
+
Percent Total Error      =  94.6%  (4857)
-
 
+
-
Percent Correct          =  27.6%  (1417)
+
Percent Correct          =  27.6%  (1417)
-
 
+
-
Percent Substitution      =  65.4%  (3358)
+
Percent Substitution      =  65.4%  (3358)
-
Percent Deletions        =    7.0%  ( 357)
+
Percent Deletions        =    7.0%  ( 357)
-
Percent Insertions        =  22.3%  (1142)
+
Percent Insertions        =  22.3%  (1142)
-
Percent Word Accuracy    =    5.4%
+
Percent Word Accuracy    =    5.4%
-
 
+
-
 
+
-
Ref. words                =          (5132)
+
Ref. words                =          (5132)
-
Hyp. words                =          (5917)
+
Hyp. words                =          (5917)
-
Aligned words            =          (6274)
+
Aligned words            =          (6274)
 +

Revision as of 16:36, 11 April 2009

Contents

Outline

  1. Intro
  2. Unit Selection
    • Mistake instance
      Unit
      Replacement
    • Multwords
  3. Baseline Description
    • Vocab: single most frequent pronunciation from a multi-pronunciation dictionary (better than multi-pronunciation)
  4. Results
    • what to emphasize? Ideally, units+DTs will beat just DTs for every number of components. Even if we cannot grow the components until improvement bottoms out, at least there will be a trend.
  5. Conclusion
    • Future work: consider context during unit selection (right now the unit is context-free - the same unit appearing in all contexts where replacements took place).

Tests for units paper

tests to run
compPer: units: monophone states Mix: totalComp: WER Test WER Important
512 1 503 256k TR
256 1 1000 256k TR
64 1 3854 256k 49.3
64 2 2000 256k  ?
32 4 2000 256k  ?
32 2 4000 256k  ?
alternatively
256 48 137 503 127971 53.0
128 48 137 1033 131185 50.9
32 48 137 3845 122907 51.4
64 112 615 2024 ~128k TR
16 4 2000 128k  ?
16 112 615 4000 128k  ?

The units make it worse

with LM_PENALTY=0

DETAILED OVERALL REPORT FOR THE SYSTEM: test/config16/test0/accuracy/out.nosil.trn

SENTENCE RECOGNITION PERFORMANCE

sentences                                         500
with errors                             89.2%   ( 446)

  with substitions                      72.4%   ( 362)
  with deletions                        26.2%   ( 131)
  with insertions                       74.4%   ( 372)


WORD RECOGNITION PERFORMANCE

Percent Total Error       =   99.1%   (5107)

Percent Correct           =   28.6%   (1476)

Percent Substitution      =   66.2%   (3411)
Percent Deletions         =    5.1%   ( 265)
Percent Insertions        =   27.8%   (1431)
Percent Word Accuracy     =    0.9%


Ref. words                =           (5152)
Hyp. words                =           (6318)
Aligned words             =           (6583)

CONFUSION PAIRS                  Total                 (2790)
                                With >=  1 occurances (2790)


with LM_PENALTY=-1

test2kUtt/config16Disaster/test0/accuracy/out.nosil.trn.dtl 
DETAILED OVERALL REPORT FOR THE SYSTEM: test2kUtt/config16/test0/accuracy/out.nosil.trn

SENTENCE RECOGNITION PERFORMANCE

 sentences                                         500
 with errors                             88.2%   ( 441)

  with substitions                      72.8%   ( 364)
  with deletions                        32.8%   ( 164)
  with insertions                       68.6%   ( 343)


WORD RECOGNITION PERFORMANCE

Percent Total Error       =   94.6%   (4857)

Percent Correct           =   27.6%   (1417)

Percent Substitution      =   65.4%   (3358)
Percent Deletions         =    7.0%   ( 357)
Percent Insertions        =   22.3%   (1142)
Percent Word Accuracy     =    5.4%


Ref. words                =           (5132)
Hyp. words                =           (5917)
Aligned words             =           (6274)
Personal tools