Large-margin minimum classification error training for large-scale speech recognition tasks

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

Volumn 4, Issue , 2007, Pages

  Yu, Dong ^a   Deng, Li ^a   He, Xiaodong ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

Discriminative training; Large margin learning; Minimum classification error training

Indexed keywords

DISCRIMINATIVE TRAINING; LARGE MARGIN LEARNING; MINIMUM CLASSIFICATION ERROR TRAINING; VOCABULARY TELEPHONY SPEECH RECOGNITION;

OPTIMIZATION; PROBLEM SOLVING; RISK MANAGEMENT; SPEECH RECOGNITION; VOCABULARY CONTROL;

ERROR ANALYSIS;

EID: 34547526577     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.367275     Document Type: Conference Paper

References (17)

1. X. He, L. Deng, and W. Chou, "A novel learning method for hidden Markov models in speech and audio processing," Proc. IEEE MMSP 2006.
2. B.-H. Juang, W. Chou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Trans. Speech Audio Proc., 1997, 5(3):257-265.
3. B.-H. Juang and S. Katagiri, "Discriminative training," ASJ Special Issue, 1992, Vol. 3, No. 6, pp. 333-339.
4. S. Katagiri, B.-H. Juang and C-H. Lee, "Pattern recognition using a generalized probabilistic descent method," Proceedings of the IEEE, 1998, Vol. 86, No. 11, pp. 2345-2373.
5. R. G. Leonard, "a database for speaker-independent digit recognition", Proc. ICASSP, 1984, 42.11.1-42.11.4.
6. J. Li, M. Yuan, and C.-H. Lee, "Soft margin estimation of hidden Markov model parameters", Proc. Interspeech 2006, pp. 2422-2425.
7. X. Li and H. Jiang, "A constrained joint optimization method for large-margin HMM estimation," Proc. ASRU Workshop, 2005, pp. 151-156.
8. X. Li, and H. Jiang, "Solving large-margin estimation of HMMs via semidefinite programming," Proc. Interspeech 2006, pp. 2414-2417.
9. C. Liu, H. Jiang, L. Rigazio, "Recent improvement on maximum relative margin estimation of HMMs for speech recognition", Proc. ICASSP 2006, Vol. 1, pp. 269-272.
10. E. McDermott. "Discriminative training for speech recognition", Ph.D. thesis, Waseda University, 1997.
11. E. McDermott, T. Hazen, J. L. Roux, A. Nakamura, and S. Katagiri, "Discriminative training for large vocabulary speech recognition using minimum classification error," IEEE Trans. Speech and Audio Proc, Vol. 14. No. 2, 2006.
12. E. McDermott and S. Katagiri, "A Parzen window based derivation of minimum classification error from the theoretical Bayes classification risk," Proc. ICSLP, 2002.
13. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig. "fMPE: Discriminatively trained features for speech recognition," Proc. DARPA EARS RT-04 Workshop, 2004, Paper No. 35, 5 pages.
14. F. Sha and L. Saul, "Large-margin Gaussian mixture modeling for phonetic classification and recognition," Proc. ICASSP 2006, Vol. 1, pp. 265-268.
15. P. C. Woodland and D. Povey, "Large-scale discriminative training for speech recognition," Proc. ITRW ASR, ISCA, 2000, pp. 7-16.
16. D. Yu, L. Deng, X. He, and A. Acero, "Use of incrementally regulated discriminative margins in MCE training for speech recognition", Proc. Interspeech 2006, pp. 2418-2421.
17. N. Kumar and A.G. Andreou, "Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition," Speech Communication, 1998, vol. 26, pp. 283-297.