ESTIMATION OF GLOBAL POSTERIORS AND FORWARD-BACKWARD TRAINING OF HYBRID HMM/ANN SYSTEMS

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 1951-1954

  Hennebert, J ^b,e   Ris, C ^a   Bourlard, H ^b,c   Renals, S ^d   Morgan, N ^b  

^a FPMS   (Belgium)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^c IDIAP RESEARCH INSTITUTE   (Switzerland)

^d UNIVERSITY OF SHEFFIELD   (United Kingdom)

^e EPFL   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION;

COMPARISON OF PERFORMANCE; FORMALISATION; GLOBAL MODELS; MODEL POSTERIORS; VITERBI;

HYBRID SYSTEMS;

EID: 85135149324     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Bourlard, H., Konig, Y. and Morgan, N., "REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities in connectionist speech recognition", Proc. EUROSPEECH'95, Madrid, September 1995.
2. Bourlard, H., Konig, Y. and Morgan, N., "A Training Algorithm for Statistical Sequence Recognition with Applications to Transition-Based Speech Recognition," IEEE Signal Processing Letters, vol. 3, no. 7, pp. 203-205, 1996.
3. Renals, S., Morgan, N., Bourlard, H., Cohen, M. and Franco, H., "Connectionist Probability Estimators in HMM Speech Recognition," IEEE Trans. on Speech and Audio Processing, vol. 2, no. 1, pp. 161-174, 1994.
4. Robinson, T., Hochberg, M. and Renals, S., "The use of recurrent networks in continuous speech recognition," in Automatic Speech and Speaker Recognition -Advanced Topics, pp. 233-258, Kluwer Academic Publishers, 1996.
5. Senior, A. and Robinson, T., "Forward-Backward Retraining of Recurrent Neural Networks," in Advances in Neural Information Processing Systems 8, MIT Press, pp. 743-749, 1996.
6. Yan,Y., Fanty M., and Cole R., "Speech Recognition Using Neural Networks with Forward Backward Probability Generated Targets," Proc. ICASSP'97, IV-3241-3244, Munich.
7. Pirelli, J. et al., "Phonebook: A Phonetically-rich isolated word telephone speech database," Proc. ICASSP'95, Detroit.
8. Dupont, S., Bourlard, H., Deroo, O., Fontaine, V. and Boite, J.-M., "Hybrid HMM/ANN Systems for Training Independent Tasks: Experiments on 'Phonebook' and Related Improvements," to be published in Proc. of ICASSP'97.
9. Hermansky, H., Morgan, N., "Rasta Processing of Speech", IEEE Transactions on Speech and Audio Processing, special issue on Robust Speech Recognition, vol.2, no.4, pp. 578-589, Oct.94