Reducing computation time of the rapid unsupervised speaker adaptation based on HMM-sufficient statistics

IEICE Transactions on Information and Systems

Volumn E90-D, Issue 2, 2007, Pages 554-561

  Gomez, Randy ^a   Toda, Tomoki ^a   Saruwatari, Hiroshi ^a   Shikano, Kiyohiro ^a  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

HMM sufficient statistics; Rapid adaptation; Speech recognition; Unsupervised

Indexed keywords

ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; REGRESSION ANALYSIS; STATISTICS;

HMM-SUFFICIENT STATISTICS; RAPID ADAPTATION; UNSUPERVISED SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 33847209621     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e90-d.2.554     Document Type: Article

References (18)

1. A. Baba, S. Yoshizawa, M. Yamada, A. Lee, and K. Shikano, "Elderly acoustic model for large vocabulary continuous speech recognition," Proc. EUROSPEECH, pp.1657-1660, 2001.
2. C. Huang, T. Chen, S. Li, and J.L. Zhou, "Analysis of speaker variability," Proc. Eurospeech, vol.2, pp.1377-1380, Sept. 2001.
3. B. Xiang, L. Nguyen, S. Matsoukas, and R. Schwartz, "Cluster- dependent acoustic modeling," Proc. ICASSP, vol.1, pp.677-680, 2005.
4. D. Pye and P.C. Woodland, "Experiments in speaker normalisation and adaptation for large vocabulary adaptation," Proc. ICASSP, vol.2, no.1, pp.1047-1051, April 1997.
5. P. Zhan, M. Westphal, M. Finke, and A. Waibel, "Speaker normalization and speaker adaptation - A combination for conversational speech recognition," Proc. Eurospeech, vol.10, pp.2087-2090, Sept. 1997.
6. D. Giuliani and M. Gerosa, "Investigating recognition of children's speech," Proc. ICASSP, vol.2, pp.137-140, April 2003.
7. C.J. Leggeter and P.C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Proc. Computer Speech and Language, vol.9, pp.171-185, 1995.
8. J. Gauvain and C.H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observation of Markov chains," IEEE Trans. Speech Audio Process., vol.2, no.2, pp.291-298, 1994.
9. C. Huang, T. Chen, and E. Chan, "Transformation and combination of hidden Markov models for speaker selection training," Proc. ICSLP, pp.1377-1380, 2004.
10. T. Matsui, T. Matsuoka, and S. Furui, "Smoothed N-best based speaker adaptation for speech recognition," Proc. ICASSP, pp.1015-1018, 1997.
11. G. Vaibhava, V. Karthik, and G. Ramesh, "Rapid adaptation with linear combinations of rank-one matrices," Proc. ICASSP, vol.1, pp.581-584, 2002.
12. R. Kuhn, F. Perronnin, P. Nguyen, J. Junqua, and L. Rigazio, "Very fast adaptation with a compact context-dependent eigenvoice model," Proc. ICASSP, vol.1, pp.373-376, 2001.
13. S. Yoshizawa, A. Baba, K. Matsunami, Y. Mera, M. Yamada, and K. Shikano, "Unsupervised speaker adaptation based on sufficent HMM statistics of selected speakers," Proc. ICASSP, pp.341-344, 2001.
14. R. Gomez, A. Lee, H. Saruwatari, and K. Shikano, "Rapid unsupervised speaker adaptation based on multi-template HMM sufficient statistics in noisy environments," Proc. EUROSPEECH, pp.296-301, 2005.
15. R. Gomez, A. Lee, T. Toda, H. Saruwatari, and K. Shikano, "Improving rapid unsupervised speaker adaptation based on HMM-sufficient statistics in noisy environments using multi-template models," IEICE Trans. Inf. & Syst., vol.E89-D, no.3, pp.998-1005, March 2006.
16. A. Lee, T. Kawahara, K. Takeda, and K. Shikano, "A new phonetic tied-mixture model for efficient decoding," Proc. ICASSP, pp.1269-1272, 2000.
17. S. Yamade, K. Matsunami, A. Baba, A. Lee, H. Saruwatari, and K. Shikano, "Spectral subtraction in noisy environments applied to speaker adaptation based on HMM sufficient statistics," Proc. ICSLP, pp.I-1045-1048, 2000.
18. R. Gomez, A. Lee, H. Saruwatari, and K. Shikano, "Speaker-class reduction for HMM-sufficient statistics adaptation using multiple acoustic models," Proc. Acoustical Society of Japan, pp.133-134, March 2005.