Minimum Word Classification Error training of HMMS for automatic speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2008, Pages 4521-4524

  Yan, Zhi Jie ^a   Zhu, Bo ^a   Hu, Yu ^a   Wang, Ren Hua ^a  

^a UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

Author keywords

Discriminative training; Minimum classification error; Minimum word classification error; Speech recognition

Indexed keywords

ACOUSTICS; INTEGRATED OPTICS; SIGNAL PROCESSING; SPEECH;

DISCRIMINATIVE TRAINING; MINIMUM CLASSIFICATION ERROR; MINIMUM WORD CLASSIFICATION ERROR; WORD CLASSIFICATION;

SPEECH RECOGNITION;

EID: 51449090385     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518661     Document Type: Conference Paper

References (15)

1. L. Bahl, P. Brown, P. de Souza, and R. Mercer, "Maximum mutual information estimation of hidden markov model parameters for speech recognition," in Proc. ICASSP1986, 1986, vol. 1, pp. 49-52.
2. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Transactions on Signal Processing, vol. 40, no. 12, pp. 3043-3054, 1992.
3. D. Povey, Discriminative Training for Large Vocabulary Speech Recognition, Ph.D. thesis, Cambridge University, 2004.
4. W. Chou, C.-H. Lee, and B.-H. Juang, "Minimum error rate training based on n-best string models," in Proc. ICASSP1993, 1993, vol. 2, pp. 652-655.
5. E. McDermott and S. Katagiri, "Minimum error training for speech recognition," in Proc. IEEE Workshop on Neural Networks for Signal Processing, 1994, pp. 259-268.
6. E. McDermott and S. Katagiri, "String-level MCE for continuous phoneme recognition," in Proc. EuroSpeech1997, 1997, vol. 1, pp. 123-126.
7. Q. Fu, X. He, and L. Deng, "Phone-discriminating minimum classification error (P-MCE) training for phonetic recognition," in Proc. InterSpeech2007, 2007, pp. 2073-2076.
8. R. Schluiter, W. Macherey, B. Müiller, and H. Ney, "Comparison of discriminative training criteria and optimization methods for speech recognition," Speech Communication, vol. 34, pp. 287-310, 2001.
9. W. Macherey, L. Haferkamp, R. Schlüiter, and H. Ney, "Investigations on error minimizing training criteria for discriminative training in automatic speech recognition," in Proc. EuroSpeech2005, 2005, pp. 2133-2136.
10. S. Young, et al., The HTK Book, 2006, Revised for HTK version 3.4.
11. Y. Normandin, Hidden Markov Models, Maximum Mutual Information Estimation, and the Speech Recognition Problem, Ph.D. thesis, McGill University, 1991.
12. D. Povey and B. Kingsbury, "Evaluation of proposed modifications to MPE for large scale discriminative training," in Proc. ICASSP2007, 2007, vol. 4, pp. 321-324.
13. S. Young, "The general use of tying in phoneme-based hmm speech recognisers," in Proc. ICASSP1992, 1992, vol. 1, pp. 569-572.
14. K. Vertanen, "HTK Wall Street Journal (WSJ) training recipe," http://www.inference.phy.cam.ac.uk/kv227/htk/.
15. P. Woodland, J. Odell, V. Valtchev, and S. Young, "Large vocabulary continuous speech recognition using HTK," in Proc. ICASSP1994, 1994, vol. 2, pp. 125-128.