Maximum relative margin estimation of HMMS based on N-best string models for continuous speech recognition

Proceedings of ASRU 2005: 2005 IEEE Automatic Speech Recognition and Understanding Workshop

Volumn 2005, Issue , 2005, Pages 420-425

  Liu, Chaojun ^a   Jiang, Hui ^b   Rigazio, Luca ^a  

^a Panasonic R and D Company of America   (United States)

^b YORK UNIVERSITY   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC WAVES; BIT ERROR RATE; CLASSIFIERS; MAXIMUM LIKELIHOOD ESTIMATION; STANDARDS; WORD PROCESSING;

DIGIT RECOGNITION; LARGE MARGIN ESTIMATION (LME); MAXIMUM RELATIVE MARGIN ESTIMATION (MRME); N-BEST STRING MODELS;

CONTINUOUS SPEECH RECOGNITION;

EID: 33846202166     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2005.1566540     Document Type: Conference Paper

References (12)

1. L.R. Bahl, P.F. Brown, P.V. de Souza, and R.L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition", Proc. of ICASSP86, pp.49-52, Tokyo, Japan, 1986.
2. W. Chou, C.-H. Lee and B.-H. Juang, "Minimum error rate training based on N-best string models", Proceedings of ICASSP93, 1993.
3. H. Jiang, F. Soong and C.-H. Lee, "A dynamic insearch data selection method with its applications to acoustic modeling and utterance verification", to appear in IEEE Trans. on SAP, Sep. 2005.
4. H. Jiang, "Discriminative training for large margin HMMs", Technical Report CS-2004-01, CSE Department, York University, March 2004.
5. B.-H. Juang, W. Chou and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Trans. on Speech and Audio Processing (SAP), pp.257-265, Vol.5, No.3, May 1997.
6. S. Katagiri, B.-H. Juang and C.-H. Lee, "Pattern recognition using a generalized probabilistic descent method," Proceedings of the IEEE, Vol. 86, No. 11, pp.2345-2373, Nov. 1998.
7. R.G. Leonard, "A database for speaker-independent digit recognition", Proceedings of ICASSP84, 1984.
8. X. Li, H. Jiang and C. Liu, "Large margin HMM for speech recognition", Proceedings of ICASSP05, May 2005.
9. C. Liu, H. Jiang and X. Li, "Discriminative training of CDHMM for maximum relative separation margin", Proceedings of ICASSP05, May 2005.
10. Y. Normandin, R. Cardin and R. Demori, "High-performance connected digit recognition using maximum mutual information estimation," IEEE Trans. on SAP, Vol. 2, No. 2, Apr. 1994.
11. V. N. Vapnik, Statistical Learning Theory, Wiley, 1998.
12. P.C. Woodland and D. Povey, "Large Scale discriminative training of hidden Markov models for speech recognition," Computer Speech & Language, pp.25-47, Vol. 16, No. 1, January 2002.