Maximum likelihood linear transformations for HMM-based speech recognition

M.J.F. Gales

doi:10.1006/csla.1998.0043

Maximum likelihood linear transformations for HMM-based speech recognition

Computer Speech & Language ◽

10.1006/csla.1998.0043 ◽

1998 ◽

Vol 12 (2) ◽

pp. 75-98 ◽

Cited By ~ 731

Author(s):

M.J.F. Gales

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Linear Transformations

Download Full-text

Maximum likelihood clustering of Gaussians for speech recognition

IEEE Transactions on Speech and Audio Processing ◽

10.1109/89.294362 ◽

1994 ◽

Vol 2 (3) ◽

pp. 453-455 ◽

Cited By ~ 32

Author(s):

A. Kannan ◽

M. Ostendorf ◽

J.R. Rohlicek

Keyword(s):

Speech Recognition ◽

Maximum Likelihood

Download Full-text

Maximum likelihood model adaptation using piecewise linear transformation for robust speech recognition

2009 IEEE 13th International Symposium on Consumer Electronics ◽

10.1109/isce.2009.5156924 ◽

2009 ◽

Author(s):

Yong Lu ◽

Zhenyang Wu

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Linear Transformation ◽

Piecewise Linear ◽

Robust Speech Recognition ◽

Model Adaptation ◽

Piecewise Linear Transformation ◽

Likelihood Model

Download Full-text

Adaptive training with noisy constrained maximum likelihood linear regression for noise robust speech recognition

10.21437/interspeech.2009-364 ◽

2009 ◽

Author(s):

D. K. Kim ◽

M. J. F. Gales

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Linear Regression ◽

Robust Speech Recognition ◽

Adaptive Training ◽

Noise Robust Speech Recognition ◽

Noise Robust ◽

Constrained Maximum Likelihood ◽

Maximum Likelihood Linear Regression

Download Full-text

A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations

10.21437/interspeech.2006-345 ◽

2006 ◽

Author(s):

Qiang Huo ◽

Donglai Zhu

Keyword(s):

Maximum Likelihood ◽

Piecewise Linear ◽

Linear Transformations ◽

Training Approach ◽

Variability Compensation

Download Full-text

Maximum-likelihood stochastic transformations for continuous speech recognition

10.12681/eadd/32036 ◽

2000 ◽

Author(s):

Βασίλειος Διακολουκάς

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Continuous Speech ◽

Continuous Speech Recognition

Download Full-text

Speech recognition in a reverberant environment using matched filter array (MFA) processing and linguistic-tree maximum likelihood linear regression (LT-MLLR) adaptation

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258) ◽

10.1109/icassp.1999.759785 ◽

1999 ◽

Cited By ~ 2

Author(s):

P. Raghavan ◽

R.J. Renomeron ◽

C. Che ◽

D.-S. Yuk ◽

J.L. Flanagan

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Linear Regression ◽

Matched Filter ◽

Filter Array ◽

Reverberant Environment ◽

Maximum Likelihood Linear Regression

Download Full-text

Reviewing Feature Non-Linear Transformations for Robust Speech Recognition

Recent Advances in Robust Speech Recognition Technology ◽

10.2174/978160805172411101010190 ◽

2012 ◽

pp. 190-196

Keyword(s):

Speech Recognition ◽

Robust Speech Recognition ◽

Linear Transformations ◽

Non Linear

Download Full-text

Signal bias removal by maximum likelihood estimation for robust telephone speech recognition

IEEE Transactions on Speech and Audio Processing ◽

10.1109/tsa.1996.481449 ◽

1996 ◽

Vol 4 (1) ◽

pp. 19 ◽

Cited By ~ 114

Author(s):

Biing-Hwang Juang ◽

M.G. Rahim

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Maximum Likelihood Estimation ◽

Likelihood Estimation ◽

Telephone Speech ◽

Bias Removal

Download Full-text

A maximum-likelihood approach to stochastic matching for robust speech recognition

IEEE Transactions on Speech and Audio Processing ◽

10.1109/89.496215 ◽

1996 ◽

Vol 4 (3) ◽

pp. 190-202 ◽

Cited By ~ 233

Author(s):

A. Sankar ◽

Chin-Hui Lee

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Robust Speech Recognition ◽

Maximum Likelihood Approach ◽

Likelihood Approach ◽

Stochastic Matching

Download Full-text

Frequency-domain maximum likelihood estimation for automatic speech recognition in additive and convolutive noises

IEEE Transactions on Speech and Audio Processing ◽

10.1109/89.841208 ◽

2000 ◽

Vol 8 (3) ◽

pp. 255-266 ◽

Cited By ~ 24

Author(s):

Y. Zhao

Keyword(s):

Speech Recognition ◽

Maximum Likelihood ◽

Maximum Likelihood Estimation ◽

Frequency Domain ◽

Automatic Speech Recognition ◽

Likelihood Estimation

Download Full-text