STRING-LEVEL MCE FOR CONTINUOUS PHONEME RECOGNITION

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

Volumn , Issue , 1997, Pages 123-126

  McDermott, Erik ^a   Katagiri, Shigeru ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION (OF INFORMATION); DATABASE SYSTEMS; SPEECH COMMUNICATION; SPEECH RECOGNITION;

DISCRIMINATIVE TRAINING; ERROR CLASSIFIERS; GENERALIZED PROBABILISTIC DESCENTS; LOSS FUNCTIONS; MAXIMUM-LIKELIHOOD ESTIMATION; MINIMUM CLASSIFICATION ERROR; MINIMUM CLASSIFICATION ERROR TRAINING; OPTIMIZATION CRITERIA; PERFORMANCE; PHONEMES RECOGNITION;

MAXIMUM LIKELIHOOD ESTIMATION;

EID: 0003840590     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Katagiri, S., Lee, C.-H. and Juang, B.-H. (1991). New Discriminative Training Algorithms Based on the Generalized Descent Method. Proceedings of the 1991 IEEE Workshop on Neural Networks for Signal Processing, August 1991, pp 1-10.
2. McDermott, E. & Katagiri, S. (1992). Prototype-Based Discriminative Training for Various Speech Units. Proceedings of the IEEE, ICASSP-92. pp. I:417-420.
3. Chou, W., Juang, B.-H. and Lee, C.-H. (1992). Segmental GPD Training of HMM Based Speech Recognizer. Proceedings of the IEEE, ICASSP-92, pp. I:473-476.
4. Singer, H. and Ostendorf, M. (1996). Maximum Likelihood Successive State Splitting. Proceedings of the IEEE, ICASSP-96. pp. II:601-604.
5. Chang, P.-C. and Juang, B.-H. (1993). Discriminative Training of Dynamic Programming Based Speech Recognizers. IEEE Transactions on Speech and Audio Processing, Vol. 1, No. 2, April 1993, pp. 135-143.
6. Chou, W., Juang, B.-H. and Lee, C.-H. (1993). Minimum Error Rate Training Based on the N-Best String Models. Proceedings of the IEEE, ICASSP-93, pp. II-652-655.
7. McDermott, E. and Katagiri, S. (1993). Prototype Based MCE/GPD Training for Word Spotting and Connected Word Recognition. Proceedings of the IEEE, ICASSP-93. pp. II:291-294.
8. Robinson, A.J. (1994). An Application of Recurrent Nets to Phone Probability Estimation. IEEE Transactions on Neural Networks, Vol. 5, No. 2, pp. 298-305, March 1994.
9. Lamel, L.F. & Gauvain, J.L. (1993). High Performance Speaker-Independent Phone Recognition Using CDHMM. Proceedings of Eurospeech, Vol. 1, pp. 121-124.
10. McDermott, E. & Katagiri, S. (1997). Discriminative Training for Speech Recognition. PhD dissertation, Waseda University, March 1997.
11. Fahlman, S.E. (1988). An Empirical Study of Learning Speech in Back-Propagation Networks. Technical Report CMU-CS-88-162, Carnegie Mellon University, September 1988.
12. Battiti, R.. (1992). First- and Second- Order Methods for Learning: Between Steepest Descent and Newton's Method. Neural Computation, Vol. 4, pp. 141-166.
13. Valchev, V. (1995). Discriminative Methods in HMM-based Speech Recognition. D. Phil dissertation, University of Cambridge, March 1995.
14. Katagiri, S. and McDermott, E. (1996). Discriminative Training - recent progress in speech recognition. In Handbook of Pattern Recognition and Computer Vision (Second edition), Chen, C.H., Pau, L.F., and Wang (eds.), P.S.P. World Scientific Publishing Company.