Don't multiply lightly: Quantifying problems with the acoustic model assumptions in speech recognition

2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings

Volumn , Issue , 2011, Pages 71-76

  Gillick, Dan ^a   Gillick, Larry ^b   Wegmann, Steven ^a,c  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b EnglishCentral Inc   (United States)

^c CISCO SYSTEMS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL; INDEPENDENCE ASSUMPTION; REAL COMPONENTS; SAMPLING PROCESS; TRANSITION MODEL; WORD ERROR RATE;

COMPUTER SIMULATION; EXPERIMENTS; HIDDEN MARKOV MODELS;

SPEECH RECOGNITION;

EID: 84858952478     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2011.6163908     Document Type: Conference Paper

References (15)

1. Gales, M.J.F., "Semi-Tied Covariance Matrices For Hidden Markov Models", IEEE Transactions on Speech and Audio Processing, 7:272-281, 1999.
2. Woodland, P. C., and Povey, D., "Large scale discriminative training of hidden Markov models for speech recognition", Computer Speech and Language, 16(1):25-47, 2002.
3. Chen, S., Kingsbury, B., Mangu, L., Povey, D., Saon, G., Soltau, H., and Zweig, G., "Advances in speech transcription at IBM under the DARPA EARS program", IEEE Transactions on Audio, Speech, and Language Processing, 14(5):1596-1608, 2006.
4. Russell, M., "A segmental HMM for speech pattern matching", Proceedings of ICASSP, 499-502, 1993.
5. Gales, M. J. F., and Young, S. J., "Segmental HMM's for speech recognition", Proceedings of EUROSPEECH, 1579-1582, 1993.
6. Ostendorf, M., Digalakis, V., and Kimball, O. A., "From HMM's to segment models: a unified view of stochastic modeling for speech recognition", IEEE Transactions on Speech and Audio Processing, 4(5):360-378, 1996. (Pubitemid 126753024)
7. Bilmes, J. A., "Buried Markov models: a graphical-modeling approach to automatic speech recognition", Computer Speech and Language, 17:(2-3):213-231, 2003.
8. Gunawardana, A., Mahajan, M., Acero, A., and Platt, J. C., "Hidden conditional random fields for phone classification", Proceedings of INTERSPEECH, 1117-1120, 2005. (Pubitemid 43908262)
9. Kuo, H.-K. J., and Gao, Y., "Maximum entropy direct models for speech recognition", IEEE Transactions on Audio, Speech, and Language Processing, 14(3):873-881, 2006. (Pubitemid 46547649)
10. McAllaster, D., Gillick, L., Scattone, F., and Newman, M., "Studies with fabricated Switchboard data: exploring sources of model-data mismatch", Proceedings of DARPA Broadcast News Transcription and Understanding Workshop, 306-310, 1998.
11. Efron, B., "The Jackknife, the Bootstrap and Other Resampling Plans", SIAM CBMS-NSF Monographs, 38, 1983.
12. Stolcke, A., "SRILM - an extensible language modeling toolkit", Proceedings of ICSLP, 901-904, 2002.
13. Woodland, P. C., Odell, J. J., Valtchev, V., and Young, S. J., "Large vocabulary continuous speech recognition using HTK", Proceedings of ICASSP, 306-310, 1994.
14. Young, S. J., Evermann, G., Gales, M. J. F., Kershaw, D., Moore, G., Odell, J. J., Ollason, D. G., Povey, D., Valtchev, V., and Woodland, P.C., "The HTK Book Version 3.4", Manual, Cambridge University Engineering Department, 2006.
15. Kruskal, W., "Miracles and statistics: The casual assumption of independence", Journal of the American Statistical Association, 83(404):929-940, 1988.