Discriminative training for large vocabulary telephone-based name recognition

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

Volumn 6, Issue , 2000, Pages 3739-3742

  McDermott, Erik ^a,c   Biem, Alain ^a   Tenpaku, Seiichi ^b   Katagiri, Shigeru ^a,c  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b Arcadia Corporation   (Japan)

^c NTT CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTICS; DECISION TREES; HIDDEN MARKOV MODELS; MARKOV PROCESSES; SPEECH RECOGNITION; TELEPHONE SETS; ACOUSTIC SIGNAL PROCESSING; APPROXIMATION THEORY; AUTOMATIC TELEPHONE SYSTEMS; ERRORS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH ANALYSIS;

ACOUSTIC ENVIRONMENT; COMMERCIAL APPLICATIONS; CONTEXT INDEPENDENT; CONTEXT-DEPENDENT MODELS; DISCRIMINATIVE TRAINING; MINIMUM CLASSIFICATION ERROR CRITERIONS; PHONETIC DECISION TREE; SPEAKER INDEPENDENTS;

SIGNAL PROCESSING; SPEECH RECOGNITION;

DISCRIMINATIVE TRAINING; HIDDEN MARKOV MODELS; MINIMUM CLASSIFICATION ERROR; NAME RECOGNITION; PHONETIC DECISION TREES;

EID: 0033694505     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.860215     Document Type: Conference Paper

References (12)

1. Biem, A., McDermott, E., Woudenberg, E. & Katagiri, S. (2000). The ATR HIP Minimum Error Classification System (MECS) for Speech Recognition. ATR HIP Technical Report.
2. Azzopardi, D., Semnani, Shahrma, S., Milner, B., and Wiseman, R. (1998). Improving Accuracy of Telephonybased, Speaker-independent Speech Recognition. Proc. IC-SLP, 1998.
3. Glass, J. R. and Hazen, T. J. (1998). Telephone-Based Conversational Speech Recognition in the JUPITER Domain. Proc. ICSLP, 1998.
4. Juang, B.-H. and Katagiri, S. (1992). Discriminative Learning for Minimum Error Classification. IEEE Transactions on Signal Processing, Vol. 40, No. 12, pp. 3043-3053.
5. McDermott, E. & Katagiri, S. (1997). Discriminative Training for Speech Recognition. PhD dissertation, Waseda University, March 1997.
6. McDermott, E. and Katagiri, S. (1994). Prototype Based Discriminative Training for Various Speech Units. Computer Speech and Language, Vol. 8, pp. 351-368.
7. Steinbiss, V., Tran, B.-H. and Ney, H. (1994). Improvements in Beam Search. Proceedings of the International Conference on Spoken Language Processing, S36-5.1, pp. 2143-2146.
8. Hermansky, H. & Morgan, N. (1994). RASTA processing of speech. IEEE Trans. on Speech and Audio Processing, vol. 2, no. 4, pp. 578-589, October 1994.
9. Young, S. J., Woodland, P. C. (1994). State clustering in hidden Markov model-based continuous speech recognition. Computer Speech and Language, Vol. 8, pp. 369-383.
10. Odell, J. J. (1995). The Use of Context in Large Vocabulary Speech Recognition. D. Phil dissertation, Cambridge University, March 1995.
11. Beulen, K., Bransch, H. & Ney, H. (1997). State tying for context dependent phoneme models. Proc. Eurospeech, 1997.
12. Willett, D., Worm, A., Neukirchen, C. and Rigoll, G. (1998). Confidence Measures for HMM-based Speech Recognition. Proc. ICSLP, 1998.