A novel estimation of feature-space MLLR for full-covariance models

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

Volumn , Issue , 2010, Pages 4310-4313

  Ghoshal, Arnab ^a   Povey, Daniel ^b   Agarwal, Mohit ^c   Akyazi, Pinar ^d   Burget, Lukáš ^e   Feng, Kai ^f   Glembek, Ondřej ^e   Goel, Nagendra ^g   Karafiát, Martin ^e   Rastrow, Ariya ^h   Rose, Richard C ⁱ   Schwarz, Petr ^e   Thomas, Samuel ^h  

^a SAARLAND UNIVERSITY   (Germany)

^b MICROSOFT RESEARCH   (United States)

^c INDIAN INSTITUTE OF INFORMATION TECHNOLOGY   (India)

^d BOGAZICI UNIVERSITY   (Turkey)

^e BRNO UNIVERSITY OF TECHNOLOGY   (Czech Republic)

^f HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

^g Go Vivace Inc   (United States)

^h JOHNS HOPKINS UNIVERSITY   (United States)

ⁱ MCGILL UNIVERSITY   (Canada)

Author keywords

Hidden Markov models; Linear algebra; Optimization methods; Speaker adaptation; Speech recognition

Indexed keywords

HIDDEN MARKOV MODELS; LINEAR ALGEBRA; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION; SIGNAL PROCESSING; TRELLIS CODES;

FEATURE SPACE; FULL COVARIANCE MODELING; GAUSSIAN MODELING; HIDDEN-MARKOV MODELS; LIKELIHOOD FUNCTIONS; LINE SEARCHES; MAXIMUM LIKELIHOOD LINEAR REGRESSION; OPTIMIZATION METHOD; PARAMETER SPACES; SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 78049381529     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495657     Document Type: Conference Paper

References (6)

1. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, no. 2, pp. 75-98, April 1998.
2. K. Visweswariah, V. Goel, and R. Gopinath, "Structuring linear transforms for adaptation using training time information," in Proc. IEEE ICASSP, 2002, vol. 1, pp. 585-588.
3. K. C. Sim and M. J. F. Gales, "Adaptation of precision matrix models on large vocabulary continuous speech recognition," in Proc. IEEE ICASSP, 2005, vol. I, pp. 97-100.
4. D. Povey et al., "Subspace gaussian mixture models for speech recognition," Submitted to ICASSP, 2010.
5. S. Axelrod et al., "Subspace constrained Gaussian mixture models for speech recognition," IEEE Trans. Speech Audio Process., vol. 13, no. 6, pp. 1144-1160, 2005.
6. D. Povey, "A Tutorial-style introduction to Subspace Gaussian Mixture Models for Speech Recognition," Tech. Rep. MSR-TR-2009-111, Microsoft Research, 2009.