A study of irrelevant variability normalization based training and unsupervised online adaptation for LVCSR

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 1357-1360

  Shi, Guangchuan ^a,b   Shi, Yu ^a   Huo, Qiang ^a  

^a MICROSOFT RESEARCH ASIA   (China)

^b SHANGHAI JIAO TONG UNIVERSITY   (China)

Author keywords

CMLLR; Irrelevant variability normalization; LVCSR; MLLR; Unsuper vised online adaptation

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; MAXIMUM LIKELIHOOD; SPEECH COMMUNICATION; SPEECH TRANSMISSION; E-LEARNING; TRANSCRIPTION;

CMLLR; IRRELEVANT VARIABILITY NORMALIZATIONS; LVCSR; MLLR; ON-LINE ADAPTATION; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; MAXIMUM-LIKELIHOOD APPROACH; MOVING WINDOW; UNSUPERVISED ONLINE ADAPTATION; WINDOW-BASED;

E-LEARNING; MAXIMUM LIKELIHOOD;

EID: 79959831198     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Roy. Statist. Soc. Ser. B, Vol. 39, No. 1, pp.1-38, 1977.
2. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, Vol. 12, pp.75-98, 1998. (Pubitemid 128383747)
3. J. J. Godfrey, E. C. Holliman, and J. McDaniel, "SWITCHBOARD: Telephone speech corpus for research and development," Proc. ICASSP-1992, pp.517-520. See also LDC website: http://www.ldc.upenn.edu-for-more-details.
4. Q. Huo and B. Ma, "Online adaptive learning of continuous-density hidden Markov models based on multiple-stream prior evolution and posterior pooling," IEEE Trans. on Speech and Audio Processing, Vol. 9, No. 4, pp.388-398, 2001. (Pubitemid 32372180)
5. Q. Huo and D. Zhu, "A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations," Proc. Interspeech-2006, pp.1129-1132.
6. Q. Huo and D. Zhu, "Robust speech recognition based on structured modeling, irrelevant variability normalization and unsupervised online adaptation," Proc. ICASSP-2009, pp.4637-4640.
7. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models," Computer Speech and Language, Vol. 9, pp.171-185, 1995.
8. NIST Scoring Toolkit SCTK, see the following site for details: http://itl.nist.gov/iad/mig/tests/rt/2002/software.htm.
9. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," Proc. ICASSP-2005, pp.961-964.
10. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach based on stochastic vector mapping," IEEE Trans. on Audio, Speech and Language Processing, Vol. 14, No. 6, pp.2147-2155, 2006.
11. J. Wu, Q. Huo, and D. Zhu, "An environment compensated maximum likelihood training approach based on stochastic vector mapping," Proc. ICASSP-2005, pp.429-432.
12. S. Young, et al., The HTK Book (for HTK version 3.4), 2006.
13. D. Zhu and Q. Huo, "A maximum likelihood approach to unsupervised online adaptation of stochastic vector mapping function for robust speech recognition," Proc. ICASSP-2007, pp. IV-773-776.
14. D. Zhu and Q. Huo, "Irrelevant variability normalization based HMM training using MAP estimation of feature transforms for robust speech recognition," Proc. ICASSP-2008, pp.4717-4720.