Utterance-based selective training for the automatic creation of task-dependent acoustic models

IEICE Transactions on Information and Systems

Volumn E89-D, Issue 3, 2006, Pages 962-969

  Cincarek, Tobias ^a,b   Toda, Tomoki ^a,b,c,d,e   Saruwatari, Hiroshi ^a,b,d,f   Shikano, Kiyohiro ^{a,b,d,e,f,g,h}  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^b Acoustical Society of Japan ASJ   (Japan)

^c ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^d IEEE

^e International Speech Communication Association

^f VR Society of Japan   (Japan)

^g Institute of Electronics   (Japan)

^h IPSJ   (Japan)

Author keywords

Acoustic modeling; Development costs; Selective training; Sufficient statistics; Task dependency

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; DATA ACQUISITION; DATABASE SYSTEMS; MATHEMATICAL MODELS; STATISTICAL METHODS;

ACOUSTIC MODELING; DEVELOPMENT COSTS; SUFFICIENT STATISTICS; TASK-DEPENDENCY;

SPEECH RECOGNITION;

EID: 33645797655     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e89-d.3.962     Document Type: Conference Paper

References (15)

1. Y. Gao, L. Gu, and H.K.J. Kuo, "Portability challenges in developing interactive dialogue systems," International Conference on Acoustics, Speech, and Signal Processing, pp.1017-1020, 2005.
2. F. Lefevre, J.L. Gauvain, and L. Lamel, "Genericity and portability for task-dependent speech recognition," Comput. Speech Lang., vol.19, pp.345-363, 2005.
3. L.M. Arslan and J.H.L. Hansen, "Selective training in hidden Markov model recognition," IEEE Trans. Speech Audio Process., vol.7, no.1, pp.46-54, 1999.
4. T.M. Kamm and G.G.L. Meyer, "Robustness aspects of active learning for acoustic modeling," Proc. International Conference on Spoken Language Processing, pp.1095-1098, 2004.
5. D. Hakkani-Tür, G. Riccardi, and A. Gorin, "Active learning for automatic speech recognition," International Conference on Acoustics, Speech, and Signal Processing, pp.3904-3907, 2002.
6. S. Yoshizawa, A. Baba, K. Matsunami, Y. Mera, M. Yamada, A. Lee, and K. Shikano, "Evaluation on unsupervised speaker adaptation based on sufficient HMM statistics of selected speakers," European Conference on Speech Communication and Technology, pp.1219-1222, 2001.
7. C. Huang, T. Chen, and E. Chang, "Transformation and combination of hidden Markov models for speaker selection training," Proc. International Conference on Spoken Language Processing, pp.1001-1004, 2004.
8. R. Nishimura, Y. Nishihara, R. Tsurumi, A. Lee, H. Saruwatari, and K. Shikano, "Takemaru-kun: Speech-oriented information system for real world research platform," International Workshop on Language Understanding and Agents for Real World Interaction, pp.70-78, 2003.
9. R. Sundaram and J. Picone, "Effects of transcription errors on supervised learning in speech recognition," International Conference on Acoustics, Speech, and Signal Processing, pp.169-172, 2004.
10. R.O. Duda, P.E. Hart, and D.G. Stork, Pattern Classification, John Wiley & Sons, 2001.
11. A.P. Dempster, N.M. Laird, and D.B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J.R. Statistical Society, vol.1, no.39, pp.1-38, 1977.
12. "Julius, an open-source large vocabulary CSR engine - http://julius.sourceforge.jp/"
13. C. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol.9, pp.171-185, 1995.
14. 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, 1994.
15. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," Proc. International Conference on Spoken Language Processing, pp.1137-1140, 1996.