Discriminative map for acoustic model adaptation

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

Volumn 1, Issue , 2003, Pages 312-315

  Povey, D ^a   Woodland, P C ^a   Gales, M J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL;

INFORMATION ANALYSIS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PERSONNEL TRAINING;

SPEECH;

EID: 0141480019     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. R. Cordoba, P.C. Woodland & M.J.F. Gales (2002). &Improved Cross-task Recognition Using MMIE Training,& ICASSP'02, Orlando, Florida.
2. M.J.F. Gales, Y Dong, D. Povey & P.C. Woodland (2003). &Porting: Switchboard to the Voicemail Task&, Submitted to ICASSP'03, Hong Kong.
3. Y. Gao, B. Ramabhadran, M. Picheny (2000). &New Adaptation Techniques for Large Vocabulary Continuous Speech Recognition,& Proc. ICSA ITRW ASR2000, Paris.
4. J. Gauvain, J & C. Lee (1994). &Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains.& IEEE Transactions on Acoustics, Speech and Signal Processing 1994, Vol.2, no. 2, pp. 291-299
5. M. Padmanabhan, B. Ramabhadran, E. Eide, G. Ramaswamy, L.R. Bahl, P.S. Gopalakrishnan & S. Roukos (1997). &Transcription of new speaking styles- Voicemail.& Proc. DARPA Hub4 Workshop.
6. D. Povey & P.C. Woodland (2002). &Minimum Phone Error and I-Smoothing for Improved Discriminative Training,& I-CASSP'02, Orlando, Florida.
7. L.F. Uebel & P.C. Woodland (2001). Discriminative Linear Transforms for Speaker Adaptation. Proc. ISCA ITR-Workshop on Adaptation Methods in Speech Recognition, Sophia-Antipolis.
8. P.C. Woodland & D. Povey (2002). &Large Scale Discriminative Training of Hidden Markov Models for Speech Recognition,& Computer Speech & Language v. 16, no 1, pp. 25-48, Jan 2002.