Discriminative cluster adaptive training

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 5, 2006, Pages 1694-1702

  Yu, Kai ^b   Gales, Mark J F ^a,b,c  

^a IEEE

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^c EMMANUEL COLLEGE   (United Kingdom)

Author keywords

Cluster adaptive training (CAT); Discriminative training; Eigenvoices; Minimum phone error (MPE); Multiple cluster HMM

Indexed keywords

CLUSTER ANALYSIS; EIGENVALUES AND EIGENFUNCTIONS; HIDDEN MARKOV MODELS; INTERPOLATION; MAXIMUM LIKELIHOOD; SPEECH RECOGNITION;

CLUSTER ADAPTIVE TRAINING (CAT); DISCRIMINATIVE TRAINING; EIGENVOICES; MINIMUM PHONE ERRORS (MPE); MULTIPLE CLUSTER HMM;

SPEECH PROCESSING;

EID: 34047260093     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.858555     Document Type: Article

References (27)

1. T. Anastasakos, J. Mcdonough, R. Schwartz, and J. Makhoul, "A compact model for speaker adaptive training," in Proc. Int. Conf. Speech Language Processing, 1996, pp. 1137-1140.
2. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density HMMs," Comput. Speech Lang., vol. 9, pp. 171-186, 1995.
3. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comput. Speech Lang., vol. 12, pp. 75-98, 1998.
4. _, "Multiple-cluster adaptive training schemes," presented at the Int. Conf. Acoustics, Speech, Signal Processing, 2001.
5. _, "Cluster adaptive training of hidden Markov models," IEEE Trans. Speech Audio Process., vol. 8, no. 4, pp. 417-428, Apr. 2000.
6. R. Kuhn, J. C. Junqua, P. Nguyen, and N. Niedzielski, "Rapid speaker adaptation in eigenvoice space," IEEE Trans. Speech Audio Process., vol. 8, no. 6, pp. 695-707, Nov. 2000.
7. L. R. Bahl, P. F. Brown, P. Souza, and R. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, 1986, pp. 49-52.
8. B. H. Juang, W. Chou, and C. H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Trans. Speech Audio Process., vol. 5, no. 2, pp. 266-277, Mar. 1997.
9. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," presented at the Int. Conf. Acoustics, Speech, Signal Processing, Orlando, FL, 2002.
10. D. Povey, "Discriminative Training for Large Vocabulary Speech Recognition," Ph.D. dissertation, Eng. Dept., Cambridge Univ., Cambridge, U.K., 2003.
11. Y. Normandin, "Hidden Markov Models, Maximum Mutual Information Estimation, and the Speech Recognition Problem," Ph.D. dissertation, Dept. Elect. Eng., McGill Univ., Montréal, QC, Canada, 1991.
12. A. Gunawardana and W. Byrne, "Discriminative speaker adaptation with conditional maximum likelihood linear regression," presented at the EuroSpeech Conf., 2001.
13. T. S. J. McDonough and A. Waibel, "On maximum mutual information speaker- adapted training," presented at the Int. Conf. Acoustics, Speech, Signal Processing, Orlando, FL, 2002.
14. L. Wang and P. C. Woodland, "Discriminative adaptive training using the MPE criterion," presented at the ASRU Conf., 2003.
15. K. Yu and M. J. F. Gales, "Discriminative Cluster Adaptive Training," Eng. Dept., Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/FINFENG/TR486, 2004.
16. _, "Adaptive training using structured transforms," presented at the Int. Conf. Acoustics, Speech, Signal Processing, 2004.
17. M. J. F. Gales, "Cluster adaptive training for speech recognition," in Proc. Int. Conf. Speech Language Processing, 1998, pp. 1783-1786.
18. X. Huang, A. Acero, and H. Hon, Spoken Language Processing. Englewood Cliffs, NJ: Prentice-Hall, 2001.
19. R. Kuhn, P. Nguyen, J. C. Junqua, L. Goldwasser, N. Niedzielski, S. Fincke, K. Field, and M. Contolini, "Eigenvoices for speaker adaptation," in Proc. Int. Conf. Speech Language Processing, 1998, pp. 1771-1774.
20. P. Nuguyen, C. Wellekens, and J. C. Junqua, "Maximum likelihood eigenspace and MLLR for speech recognition in noisy environments," in Proc. Eurospeech, 1999, pp. 2519-2522.
21. J. L. Gauvain and C. H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," in IEEE Trans. Speech Audio Process., vol. 2, Jan. 1994, pp. 291-298.
22. P. C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models for speech recognition," Comput. Speech Lang., vol. 16, pp. 25-48, 2002.
23. D. Povey, M. J. F. Gales, D. Y. Kim, and P. C. Woodland, "MMI-MAP and MPE-MAP for acoustic model adaptation," presented at the EuroSpeech Conf., 2003.
24. M. J. F. Gales, "Acoustic factorization," presented at the ASRU Conf., 2001.
25. L. Gillick and S. Cox, "Some statistical issues in the comparison of speech recognition," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1989, pp. 532-535.
26. P. Nguyen, R. Kuhn, L. Rigazio, J. C. Junqua, and C. Wellekens, "Self-adaptation using eigenvoices for large-vocabulary continuous speech recognition," presented at the ITRW Adaptation Conf., 2001.
27. H. Botterweck, "Very fast adaptation for large vocabulary continuous speech recognition using eigenvoices," in Proc. Int. Conf. Speech Language Processing, 2000, pp. 354-357.