Fast model selection based speaker adaptation for nonnative speech

IEEE Transactions on Speech and Audio Processing

Volumn 11, Issue 4, 2003, Pages 298-307

  He, Xiaodong ^a   Zhao, Yunxin ^a  

^a UNIVERSITY OF MISSOURI   (United States)

Author keywords

Maximum expected likelihood; Model selection; Normative speech recognition; Speaker adaptation

Indexed keywords

MAXIMUM LIKELIHOOD ESTIMATION; REGRESSION ANALYSIS; SPEECH ANALYSIS;

SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 0042594404     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2003.814379     Document Type: Article

References (25)

1. G. Zavaliakos, R. Schwartz, and J. Makhoul, "Batch, incremental and instantaneous adaptation techniques for speech recognition," in Proc. ICASSP, 1995, pp. 676-679.
2. G. Zavaliakos, "Maximum a posteriori adaptation for large scale HMM recognizers," in Proc. ICASSP, 1996, pp. 725-728.
3. S. Witt and S. Young, "Off-line acoustic modeling of nonnative accents," in Proc. EUROSPEECH, 1999, pp. 1367-1370.
4. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, pp. 171-185, 1995.
5. J. L. Gauvain and C. H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Processing, vol. 2, pp. 291-298, Apr. 1994.
6. U. Uelber and M. Boros, "Recognition of nonnative german speech with multilingual recognizers," in Proc. EUROSPEECH, 1999, pp. 911-914.
7. V. Fischer, E. Janke, S. Kunzmann, and T. Ross, "Multilingual acoustic models for the recognition of nonnative speech," in Proc. Automatic Speech Recognition and Understanding Workshop, 2001.
8. J. Kohler, "Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds," in Proc. ICSLP, 1996, pp. 2195-2198.
9. F. Weng et al., "A study of multilingual speech recognition," in Proc. EUROSPEECH, 1997.
10. T. Schultz and A. Waibel, "Multilingual and crosslingual speech recognition," in Proc. DARPA Broadcast News Transcription and Understanding Workshop, 1998.
11. W. Byrne et al., "Toward language independent acoustic modeling," in Proc. ICASSP, 2000, pp. 1029-1032.
12. V. Diakoloukas and V. Digalakis, "Maximum likelihood stochastic transformation adaptation of hidden markov models," IEEE Trans. Speech Audio Processing, pp. 177-187, March 1999.
13. C. Boulis and V. Digalakis, "Fast speaker adaptation of large vocabulary continuous density HMM speech recognizer using a basis transform approach," in Proc. ICASSP, vol. 2, 2000, pp. 989-992.
14. D. Compernolle, "Recognizing speech of goats, wolves, sheep and ... nonnatives," Speech Commun., vol. 35, pp. 71-79, 2001.
15. S. J. V. Wijingaarden, "Intelligibility of native and nonnative dutch speech," Speech Commun., vol. 35, pp. 103-113, 2001.
16. K. Berkling, "SCoPE, syllable core and periphery evaluation: Automatic syllabification and foreign accent identification," Speech Commun., vol. 35, pp. 125-138, 2001.
17. X. He and Y. Zhao, "Model complexity optimization for nonnative English speakers," in Proc. EUROSPEECH, Scandinavia, Denmark, Sept. 2001, pp. 1461-1464.
18. _, "Fast model adaptation and complexity selection for nonnative speakers," in Proc. ICASSP, vol. 1, 2002, pp. 577-580.
19. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. New York: Springer-Verlag, 2001.
20. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree based state tying for high accuracy modeling," in Proc. ARPA Workshop on Human Language Technology, Mar. 1994.
21. S. Wang and Y. Zhao, "Online bayesian tree structure transformation of HMM's with optimal model selection for speaker adaptation," IEEE Trans. Speech Audio Processing, vol. 9, pp. 663-677, Sept. 2001.
22. S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book, Version 2.2. [Online]. Available: http://htk.eng.cam.ac.uk/docs/docs.shtml
23. G. Schwarz, "Estimating the dimension of a model," Ann. Statist., vol. 6, pp. 461-464, 1978.
24. S. Deligne, E. Eide, R. Gopinath, D. Kanevsky, B. Maison, P. Olsen, H. Printz, and J. Sedivy, "Low-resource speech recognition of 500-word vocabularies," in Proc. EUROSPEECH, 2001.
25. M. J. F. Gales and P. C. Woodland, "Mean and variance adaptation within the MLLR framework," Comput. Speech Lang., vol. 10, pp. 249-264, 1996.