Minimum error classification training of HMMs- Implementation details and experimental results

Journal of the Acoustical Society of Japan (E)

Volumn 13, Issue 6, 1992, Pages 379-387

  Rainton, David ^a   Sagayama, Shigeki ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Discriminant training; Hidden Markov modelling; Minimum error classification; Speech recognition

Indexed keywords

EID: 85007758082     PISSN: 03882861     EISSN: None     Source Type: Journal    
DOI: 10.1250/ast.13.379     Document Type: Article

References (7)

1. A. Ljolje, Y. Ephraim, and L. R. Rabiner, “Estimation of hidden Markov model parameters by minimizing empirical error rate,” Proc. ICASSP-90, 709–712 (1990).
2. H. Franco and A. Serralheiro, “Training HMMs using a minimum error approach,” Proc. ICASSP-91, 357–360 (1991).
3. S. Katagiri, C. H. Lee, and B. H. Juang, “A generalized probabilistic descent method,” Proc. Autumn Meet. Acoust. Soc. Jpn. 2-p-6, 141–142 (1990).
4. S. Katagiri, C. H. Lee, and B. H. Juang, “New discriminative algorithms based on the generalized probabilistic descent method,” Proc. IEEE-SP Workshop Neural Networks for Signal Processing, Princeton, Sept. (1991).
5. S. Katagiri, C. H. Lee, and B. H. Juang, “Discriminative multi layer feedforward networks,” Proc. IEEE-SP Workshop Neural Networks for Signal Processing, Princeton, Sept. (1991).
6. P. C. Chang, S. H. Chen, and B. H. Juang, “Discriminative analysis of distoration sequences in speech recognition,” Proc. ICASSP-91, 549–552 (1991).
7. L. E. Scales, Introduction to Non-linear Optimization, Macmillan Computer Science Series (Macmillan, London, 1985).