Automatic Speech Recognition:

You are here: / Recognition / Fundamentals / Production / Tutorials / Software / Home

4.3.4 Scoring: Converting Recognition Output and Generating a Scoring Report

The output file generated in Sections 4.2.5 a text Sof format and contains an annotation graph representation for each utterance. To convert this file to a format that can be used by NIST for scoring, go to the following directory

$ISIP_TUTORIAL/sections/s04/s04_03_p04/

and run the following command:

isip_extract_hypo -level word -format NIST_TRN -list $ISIP_TUTORIAL/databases/lists/identifiers_test.sof -exclude exclude_symbols.sof -output ./results.score -debug brief $ISIP_TUTORIAL/sections/s04/s04_02_p05/results.out

Expected Output:

  
  loading transcription database: /ftp/pub/research/isip/projects/speech/software/tutorials/
production/fundamentals/current/examples/sections/s04/s04_02_p05/results.out
  
  retrieving transcription for identifier: ah_111a, level: word
  
  retrieving transcription for identifier: ah_1a, level: word
  
  retrieving transcription for identifier: ah_27o6571a, level: word
  
  retrieving transcription for identifier: ah_2o5a, level: word
  
  retrieving transcription for identifier: ah_3b, level: word
  
  retrieving transcription for identifier: ah_416a, level: word
  
  retrieving transcription for identifier: ah_4b, level: word

  ...

The hypothesized transcriptions will be extracted from the annotation graph and stored in the file results.score in NIST scoring format.

Next, we will do the same for the reference transcriptions. Run the command:

isip_extract_hypo -level word -format NIST_TRN -list $ISIP_TUTORIAL/databases/lists/identifiers_test.sof -output ./reference.score -exclude exclude_symbols.sof -debug brief $ISIP_TUTORIAL/databases/db/tidigits_trans_word_test_db.sof

The reference transcriptions will be extracted from the annotation graph and stored in the file reference.score in NIST scoring format.

Now that the hypothesis and reference transcriptions have been converted to the appropriate format, we can use the tool isip_eval to generate a scoring report. From the same directory, run the command:

isip_eval score results.score reference.score results

Expected output:

/usr/local/sctk/bin/sclite -F -i swb -r reference.score-h results.score -o dtl all 
sclite: 2.2 TK Version 1.2
Begin alignment of Ref File: 'reference.score' and Hyp File: 'results.score'
    Alignment# 18 for speaker ah          
    Alignment# 17 for speaker ar          
    Alignment# 17 for speaker at          
    Alignment# 17 for speaker bc          
    Alignment# 17 for speaker be          
    Alignment# 17 for speaker bm          
    Alignment# 17 for speaker bn          
    Alignment# 17 for speaker cc          
    Alignment# 17 for speaker ce          
    Alignment# 17 for speaker cp          
    Alignment# 17 for speaker df          
    Alignment# 18 for speaker dj          
    Alignment# 17 for speaker ed          
    Alignment# 17 for speaker ef          
    Alignment# 17 for speaker et          
    Alignment# 17 for speaker fa          
    Alignment# 17 for speaker fg          
    Alignment# 17 for speaker fh          
    Alignment# 17 for speaker fm          
    Alignment# 11 for speaker fp          

    Writing scoring report to 'results.score.sys'
    Writing raw scoring report to 'results.score.raw'
    Writing overall detailed scoring report 'results.score.dtl'
    Writing string alignments to 'results.score.pra'

Successful Completion

===============================================================================

SENTENCE RECOGNITION PERFORMANCE

 sentences                                         336
 with errors                             10.1%   (  34)

   with substitions                       0.6%   (   2)
   with deletions                         0.0%   (   0)
   with insertions                        9.5%   (  32)


WORD RECOGNITION PERFORMANCE

Percent Total Error       =    3.6%   (  39)

Percent Correct           =   99.8%   (1082)

Percent Substitution      =    0.2%   (   2)
Percent Deletions         =    0.0%   (   0)
Percent Insertions        =    3.4%   (  37)

The command has generated a scoring report called results.report. The contents of this file are discussed in the next section.

Glossary / Help / Support / Site Map / Contact Us / IES Home