A study of an irrelevant variability normalization based discriminative training approach for LVCSR

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 5308-5311

  Zhang, Yu ^a,b   Xu, Jian ^a,c   Yan, Zhi Jie ^a   Huo, Qiang ^a  

^a MICROSOFT RESEARCH ASIA   (China)

^b SHANGHAI JIAO TONG UNIVERSITY   (China)

^c UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

Author keywords

acoustic modeling; discriminative training; irrelevant variability normalization; LVCSR; unsupervised adaptation

Indexed keywords

ACOUSTIC MODELING; DISCRIMINATIVE TRAINING; IRRELEVANT VARIABILITY NORMALIZATION; LVCSR; UNSUPERVISED ADAPTATION;

CONTINUOUS SPEECH RECOGNITION; FEATURE EXTRACTION; HIDDEN MARKOV MODELS; SIGNAL PROCESSING; SPEECH TRANSMISSION; STEREOPHONIC BROADCASTING; TELEPHONE SYSTEMS; TRANSCRIPTION;

SPEECH COMMUNICATION;

EID: 80051633248     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947556     Document Type: Conference Paper

References (8)

1. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, Vol. 12, pp.75-98, 1998.
2. 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.
3. A. Gunawardana, "Maximum Mutual Information Estimation of Acoustic HMM Emission Densities," CLSP Research Note, Note No. 40, CLSP, Johns Hopkins University, 2000.
4. 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.
5. NIST Scoring Toolkit SCTK, see the following site for details: http://itl.nist.gov/iad/mig/tests/rt/2002/software.htm.
6. D. Povey, "Discriminative Training for Large Vocabulary Speech Recognition," Ph.D. thesis, Cambridge University, 2004.
7. G.-C. Shi, Y. Shi, and Q. Huo, "A study of irrelevant variability normalization based training and unsupervised online adaptation for LVCSR," Proc. Interspeech-2010, pp.1357-1360.
8. S. Young, et al., The HTK Book (for HTK version 3.4), 2006.