Task adaptation of acoustic and language models based on large quantities of data

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 1977-1980

  Visweswariah, K ^a   Gopinath, R ^a   Goel, V ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS;

ACOUSTIC AND LANGUAGE MODELS; BASELINE SYSTEMS; CONVERSATIONAL SYSTEMS; LARGE AMOUNTS; TASK ADAPTATION; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 85009063838     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. L. Lamel, J. L. Gauvain, and G. Adda, "Unsupervised acoustic model training," in Proceedings of ICASSP, 2002, pp. 877-880.
2. A. Gunawardana and A. Acero, "Adapting acoustin models to new domains and conditions using untranscribed data," in Proceedings of Eurospeech, 2003.
3. M. Bacchiani and B. Roark, "Unsupervised language model adaptation," in Proceedings of ICASSP, 2003.
4. F. Jelinek, Statistical methods for speech recognition, The MIT press, 1998.
5. J. L. Gauvain and C. H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Transactions on speech and audio processing, pp. 291-298, 1994.
6. B. Maison and R. Gopinath, "Robust confidence annotation and rejection for continuous speech recognition," in Proceedings of ICASSP, 2001.
7. D. H. Tur, G. Riccardi, and A. Gorin, "Active learning for automatic speech recognition," in Proceedings of ICASSP, 2002.