Semi-supervised GMM and DNN acoustic model training with multi-system combination and confidence re-calibration

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2013, Pages 2360-2364

  Huang, Yan ^a   Yu, Dong ^a   Gong, Yifan ^a   Liu, Chaojun ^a  

^a MICROSOFT   (United States)

Author keywords

Confidence re calibration; Importance sampling; Semi supervised acoustic model training; System combination

Indexed keywords

CALIBRATION; HIDDEN MARKOV MODELS; IMPORTANCE SAMPLING; TRANSCRIPTION;

ACOUSTIC MODEL TRAININGS; CONFIDENCE SCORE; DEEP NEURAL NETWORKS; GAUSSIAN MIXTURE MODEL; PHONE ERROR RATE; RECALIBRATIONS; SYSTEM COMBINATION; WORD ERROR RATE REDUCTIONS;

SEARCH ENGINES;

EID: 84906218045     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Lamel, L. F., Gauvain, J. L., Smith, J. O. and Adda, G., "Unsupervised Acoustic Model Training", 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Volume: 1, Page(s): 877 - 880, 13-17 May 2002.
2. Lamel, L. F., Gauvain, J. L., Smith, J. O. and Adda, G., "Investigating Lightly Supervised Acoustic Model Training", 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Volume: 1, Page(s): 477 - 480, 7-11 May 2001.
3. Wessel, F. and Herrmann, N. J., "Unsupervised Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition", IEEE Transactions on Audio, Speech, and Language Processing (TASLP), Volume: 13, Issue: 1, Page(s): 23 - 31, Jan 2005.
4. Yu, K., Gales, M, Wang, L., and Woodland, P. C., "Unsupervised Training and Directed Manual Transcription for LVCSR", Journal of Speech Communication, Vol. 52, Issue 7-8, Page(s): 652-663, July 2010.
5. Yu, K., Gales, M.J.F., and Woodland, P.C., "Unsupervised Training for Mandarin Broadcast News and Conversation Transcription", 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 4, Page(s): 353-356, 2007.
6. Yu, K., Gales, M.J.F., and Woodland, P.C., "Unsupervised Training with Directed Manual Transcription for Recognizing Mandarin Broadcast Audio", 8th Annual Conference of the International Speech Communication Association (Interspeech), August 2007.
7. Ma, J., Matsoukas, S., Kimball, O., and Schwartz, R., "Unsupervised Training on Large Amount of Broadcast News Data", 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 2, Page(s): 349-352, May 2006.
8. Zhang R. and Rudnicky E.I., "Improving the Rerformance of an LVCSR System through Ensembles of Acoustic Models", 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 1, Page(s): 876-879, April, 2003.
9. Hakkani-tr, D. and Riccardi, G., "Theory and Applications to Automatic Speech Recognition", IEEE Transactions on Speech and Audio Processing (TASLP), Volume: 13, Issue: 4, Page(s): 504 - 511, 2005.
10. Hakkani-tr, D., Riccardi, G., and Gorin, A., "Active Learning for Automatic Speech Recognition", 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Volume: 1, Page(s):3904-3907, 13-17 May 2002.
11. Kamm, T.M. and Meyer, G.G.L., "Selective Sampling of Training Data for Speech Recognition", Proceedings of the 2nd International Conference on Human Language Technology Research, Page(s): 20-24, 2002.
12. Dahl, G.E., Yu, D., Deng, L., and Acero, A., "Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition", IEEE Transactions on Audio, Speech, and Language Processing (TASLP) - Special Issue on Deep Learning for Speech and Language Processing, Volume: 1, No. 1, Page(s): 33- 42, Jan 2012.
13. Povey, D, Kingsbury, B., Mangu, L., Saon, G., Soltau, H., and Zweig, G., "fMPE: Discriminatively Trained Features for Speech Recognition", 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Volume: 1, Page(s): 961 - 964, March 2005.
14. Povey, D, Kingsbury, B., Ramabhadran, B., Saon, G., Soltau H., and Visweswariah, K., "Boosted MMI for model and featurespace discriminative training", 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Page(s): 4057 - 4060, March 2008.
15. Fiscus, J. G., "A Post-Processing System to Yield Reduced Word Error Rates: Recognizer Output Voting Error Reduction (ROVER)", 1997 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Page(s): 347 - 354, 14-17 Dec 1997.