FABRICATING CONVERSATIONAL SPEECH DATA WITH ACOUSTIC MODELS: A PROGRAM TO EXAMINE MODEL-DATA MISMATCH

5th International Conference on Spoken Language Processing, ICSLP 1998

Volumn , Issue , 1998, Pages

  McAllaster, Don ^a   Gillick, Larry ^a   Scattone, Francesco ^a   Newman, Mike ^a  

^a Dragon Systems Inc ^*  (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FABRICATION; SPEECH;

ACOUSTICS MODEL; CONVERSATIONAL SPEECH; DATA MISMATCH; DEVELOPMENT MODEL; MODELING DATA; SIMPLE++; SPEECH DATA; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 84943154470     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. LVCSR Hub 5 Workshop Proceedings, 1995, 1996, 1997.
2. 1996 CLSP/JHU Workshop on Innovative Techniques for Large Vocabulary Continuous Speech Recognition, July 15 - August 23, 1996, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD 21218
3. Steven Greenberg, Joy Hollenback, Dan Ellis, “Insights into spoken language gleaned from phonetic transcription of the Switchboard corpus”, Proceedings Addendum, ICSLP'96, pp. 24-27
4. B. Peskin et al. “Progress in Recognizing Conversational Telephone Speech,” Proc. ICASSP-97, Munich, April 1997.
5. B. Byrne et al., “Pronunciation Modeling for Conversational Speech Recognition: A Status Report from WS97,” IEEE ASRU Workshop, Santa Barbara, December 1997.