A regularized discriminative training method of acoustic models derived by minimum relative entropy discrimination

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 2954-2957

  Kubo, Yotaro ^a,c   Watanabe, Shinji ^b   Nakamura, Atsushi ^b   Kobayashi, Tetsunori ^a  

^a WASEDA UNIVERSITY   (Japan)

^b Nippon Telegraph and Telephone Corporation   (Japan)

^c RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Discriminative training; Optimization; Speech recognition

Indexed keywords

CONVEX OPTIMIZATION; OPTIMIZATION; SPEECH COMMUNICATION; SPEECH RECOGNITION; ENTROPY;

APPROXIMATION METHODS; CUTTING PLANE ALGORITHMS; DISCRIMINATIVE TRAINING; MINIMUM RELATIVE ENTROPY; OPTIMIZATION METHOD; PHONEME RECOGNITION; REALIZATION METHOD; REGULARIZATION TECHNIQUE; ACOUSTICS MODEL; BAYESIAN; OPTIMISATIONS; TRAINING METHODS;

MINIMUM ENTROPY METHODS; SPEECH RECOGNITION;

EID: 79959828521     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. L. Bahl, P. Brown, P. de Souza, and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in Proc. ICASSP, 1986, pp. 49-52. (Pubitemid 17484870)
2. E. McDermott and S. Katagiri, "String-level MCE for continuous phoneme recognition," in Proc. EUROSPEECH, 1997, pp. 123-126.
3. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002, pp. I-105-I-108.
4. B. E. Boser, I. M. Guyon, and V. N. Vapnik, "A training algorithm for optimal margin classifiers," in Proc. 5th COLT, 1992, pp. 144-152.
5. F. Sha, "Large margin training of acoustic models for speech recognition," Ph.D. dissertation, Univ. of Pennsylvania, 2006.
6. D. Yu, L. Deng, X. He, and A. Acero, "Large-margin minimum classification error training: A theoretical risk minimization perspective," Computer Speech and Language, pp. 415-429, 2008. (Pubitemid 351614981)
7. T. S. Jaakkola, M. Meila, and T. Jebara, "Maximum entropy discrimination," Advances in Neural Information Processing Systems, vol. 12, pp. 470-476, 2000.
8. F. Valente and C. Wellekens, "Maximum entropy discrimination (MED) feature subset selection for speech recognition," in Proc. ASRU, 2003, pp. 327-332.
9. D. P. Lewis, "Combining kernels for classification," Ph.D. dissertation, Columbia Univ., 2008.
10. Y. Kubo, S. Watanabe, A. Nakamura, E. McDermott, and T. Kobayashi, "A sequential pattern classifier based on hidden markov kernel machine and its application to phoneme classification," IEEE J. Sel. Topics in Signal Process., 2010 (to appear).
11. I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun, "Large margin methods for structured and interdependent output variables," J. Mach. Learn. Research, vol. 6, pp. 1453-1484, 2005.
12. K.-F. Lee and H.-W. Hon, "Speaker-independent phone recognition using hidden Markov models," Acoust., Speech, Signal Process., IEEE Trans. on, vol. 37, no. 11, pp. 1641-1648, 1989.
13. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for model and feature-space discriminative training," in Proc. ICASSP, 2008, pp. 4057-4060.