Minimum classification error training of landmark models for real-time continuous speech recognition

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

Volumn 1, Issue , 2004, Pages

  McDermott, Erik ^a   Hazen, Timothy J ^b  

^a NTT Communication Science Laboratories   (Japan)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; ERRORS; FUNCTIONS; MATHEMATICAL MODELS; OPTIMIZATION; REAL TIME SYSTEMS; RISK MANAGEMENT;

COMPUTATION TIME; FOREGROUND NOISES; LOSS FUNCTIONS; PARTIAL WORDS;

SPEECH RECOGNITION;

EID: 4544287474     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. W. Chou, C.-H. Lee, and B.-H. Juang, "Minimum error rate training based on N-best string models," in Proc. of ICASSP, 1993, vol. 2, pp. 652-655.
2. E. McDermott, A. Biem, S. Tenpaku, and S. Katagiri, "Discriminative training for large vocabulary telephone-based name recognition," in Proc. of ICASSP, 2000, vol. 6, pp. 3739-3742.
3. P.C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models for speech recognition," Computer Speech and Language, vol. 16, pp. 25-47, 2002.
4. E. McDermott, Discriminative Training for Speech Recognition, Ph.D. thesis, Waseda University, School of Engineering, March 1997.
5. R. Schluter, W. Macherey, B. Muller, and H. Ney, "Comparison of discriminative training criteria and optimization methods for speech recognition," Speech Communication, vol. 34, pp. 287-310, 2001.
6. H. Jiang, O. Siohan, F.-K. Soong, and C-.H-. Lee, "A dynamic in-search discriminative training approach for large vocabulary speech recognition," in Proc. ICASSP 2002, 2002, vol. 1, pp. 113-116.
7. V. Zue et al., "JUPITER: A telephone-based conversational interface for weather information," IEEE Trans. on Speech and Audio Processing, vol. 8, no. 1, pp. 85-96, January 2000.
8. J. Glass, "A probabilistic framework for segment-based speech recognition," Computer Speech and Language, vol. 17, no. 2-3, pp. 137-152, April-July 2003.
9. S. E. Fahlman, "An empirical study of learning speed in back-propagation networks," Tech. Rep., Carnegie Mellon University, 1988.
10. C. Meyer and G. Rose, "Improved noise robustness by corrective and rival training," in Proc. ICASSP 2001, 2001, vol. 1, pp. 293-296.
11. T. Hazen, S. Seneff, and J. Polifroni, "Recognition confidence scoring for use in speech understanding systems," Computer Speech and Language, vol. 16, no. 1, pp. 49-67, January 2002.
12. I. Bazzi and J. Glass, "A multi-class approach for modelling out-of-vocabulary words," in Proc. of ICSLP, Denver, Colorado, September 2002, pp. 1613-1616.