Rapid speaker adaptation using clustered maximum-likelihood linear basis with sparse training data

IEEE Transactions on Audio, Speech and Language Processing

Volumn 16, Issue 3, 2008, Pages 607-616

  Tang, Yun ^a   Rose, Richard ^a  

^a MCGILL UNIVERSITY   (Canada)

Author keywords

Cluster adaptive training; Eigenvoices; Parameter tying; Speaker adaptation; Speech recognition

Indexed keywords

ADAPTATION METHODS; AUTOMATIC SPEECH RECOGNITION; BASIS VECTORS; CLUSTER ADAPTIVE TRAINING; COMPUTER MEMORIES; EIGENVOICES; GENERAL CLASS; LINEAR COMBINATIONS; LOW COMPLEXITY; MAXIMUM-LIKELIHOOD; MAXIMUM-LIKELIHOOD ESTIMATIONS; PARAMETER TYING; PERFORMANCE IMPROVEMENTS; RAPID SPEAKER ADAPTATIONS; RESOURCE MANAGEMENTS; SPACE-BASED; SPEAKER ADAPTATION; STORAGE REQUIREMENTS; TASK DOMAINS; TRAINING DATUM; WALL STREET JOURNALS; WORD ERROR RATE REDUCTIONS; WORD ERROR RATES;

MAXIMUM LIKELIHOOD ESTIMATION; RESOURCE ALLOCATION; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 64949158419     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2008.916530     Document Type: Article

References (29)

1. P. C. Woodland, "Speaker adaptation for continuous density HMMs: A review," in Proc. ITRW Adaptation Methods for Speech Recognition, Sophia Antipolis, France, 2001, pp. 11-19.
2. J. L. Gauvain and C. H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol. 2, no. 2, pp. 291-298, Apr. 1994.
3. C. J. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, no. 2, pp. 171-186, 1995.
4. 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.
5. P. Nguyen, C. Wellekens, and J. C. Junqua, "Maximum likelihood eigenspace and MLLR for speech recognition in noisy environments," in Proc. Eur. Conf. Speech Commun. Technol., Budapest, Hungary, 1999, pp. 2519-2522.
6. H. Botterweck, "Very fast adaptation for large vocabulary continuous speech recognition using eigenvoices," in Proc. Int. Conf. Spoken Lang. Process., Beijing, China, 2000, pp. 354-357.
7. T. J. Hazen, "A comparison of noval techniques for rapid speaker adaptation," Speech Commun., vol. 31, pp. 15-33, 2000.
8. B. Mak, T. C. Lai, and R. Hsiao, "Improving reference speaker weighting adaptation by the use of maximum-likelihood reference speakers," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Toulouse, France, 2006, pp. 229-232.
9. T. C. Lai and B. Bak, "Unsupervised speaker adaptation using reference speaker weighting," in Proc. Int. Symp. Chinese Spoken Lang. Process., Singapore, Dec. 2006, pp. 380-389. [10] M. J. F. Gales, "Cluster adaptive training of hidden Markov models," IEEE Trans. Speech Audio Process., vol. 8, no. 4, pp. 417-428, 2000.
10. H. Botterweck, "Anisotropic MAP defined by eigenvoices for large vocabulary continuous speech recognition," in IEEE Proc. Int. Conf. Acoust., Speech, Signal Process., Salt Lake, UT, 2001, pp. 353-356.
11. P. Kenny, G. Boulianne, and P. Dumouchel, "Eigenvoiee modeling with sparse training data," IEEE Trans. Speech Audio Process., vol. 13, no. 3, pp. 345-354, May 2005.
12. K. T. Chen, W. W. Liau, H. M. Wang, and L. S. Lee, "Fast speaker adaptation using eigenspace-based maximum likelihood linear regression," in Proc. Int. Conf. Spoken Lang. Process., Beijing, China, 2000, pp. 742-745.
13. B. Mak and R. Hsiao, "Kernel eigenvoiee speaker adaptation," IEEE
14. Trans. Speech Audio Process., vol. 13, no. 5, pp. 984-992, Sep. 2005.
15. B. Mak and R. Hsiao, "Kernel eigenspace-based MLLR adaptation," IEEE Trans. Audio, Speech, Language Process., vol. 15, no. 3, pp. 784-795, Mar. 2007.
16. K. Yu and M. J. F. Gales, "Discriminative cluster adaptive training," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1694-1703, Sep. 2006.
17. B. Zhou and J. Hansen, "Rapid discriminative acoustic model based on eigenspace mapping for fast speaker adaptation," IEEE Trans. Speech Audio Process., vol. 13, no. 4, pp. 554-564, Jul. 2005.
18. I. T. Jolliffe, Principle Component Analysis. New York: Springer-Verlag, 1986.
19. M. E. Tipping and C. M. Bishop, "Mixtures of probabilistic principal component analyzers," Neural Comput., vol. 11, no. 2, pp. 443-482, 1999.
20. D. K. Kim and N. S. Kim, "Bayesian speaker adaptation based on probabilistic pricipal component analysis," in Proc. Int. Conf. Spoken Lang. Process., Beijing, China. 2000, pp. 734-737.
21. P. Price, W. M. Fisher, J. Bernstein, and D. S. Pallett, "The DARPA 1000-word resource management database for continuous speech recognition," in Proc. IEEE Proc. Int. Conf. Acoust., Speech, Signal Process., New York, Apr. 1988, pp. 651-654.
22. D. B. Paul and J. M. Baker, "The design of the wall street journal-based CSR corpus," in Proc. IEEE DARPA Speech Natural Lang. Workshop, Austin, TX, Feb. 1992, pp. 357-360.
23. M. Gales and P. Woodland, "Mean and variance adaptation within the MLLR framework," Comput. Speech, Lang., vol. 10, no. 4, pp. 249-264, 1996.
24. S. Tsuge, M. Shishibori, K. Kita, F. Ren, and S. Kuroiwa, "Study of intra-speaker's speech variability over long and short time periods for speech recognition," in IEEE Pwc. Int. Conf. Acoust., Speech, Signal Process., Toulouse, France, May 2006, pp. I-397-I-400.
25. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc, ser. B, vol. 39, pp. 1-38, 1977.
26. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. Int. Conf Spoken Lang. Process., Philadelphia, PA, 1996, pp. 1137-1140.
27. M. Gales, "Maximum likelihood linear teansformations for HMM-based speech recognition," Comput. Speech Lang., vol. 12, pp. 75-98, 1998.
28. S. Roweis and L. K. Saul, "Nonlinear dimensionality reduction by locally linear embedding," Science, vol. 290, pp. 2323-2326, 2000.
29. M. Belkin and P. Niyogi, "Laplacian eigenmaps and spectral techniques for embedding and clustering," in Proc. Adv. Neural Inf. Process. Syst. 14, 2001, pp. 585-591.