Minimum bayes risk estimation and decoding in large vocabulary continuous speech recognition

IEICE Transactions on Information and Systems

Volumn E89-D, Issue 3, 2006, Pages 900-907

  Byrne, William ^a,b  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b Johns Hopkins University   (United States)

Author keywords

Acoustic modeling; Automatic speech recognition; Discriminative training; Maximum mutual information

Indexed keywords

DECODING; IDENTIFICATION (CONTROL SYSTEMS); IMAGE SEGMENTATION; MARKOV PROCESSES; MATHEMATICAL MODELS; RISK ASSESSMENT;

ACOUSTIC MODELING; AUTOMATIC SPEECH RECOGNITION; DISCRIMINATIVE TRAINING; MAXIMUM MUTUAL INFORMATION;

SPEECH RECOGNITION;

EID: 33645766076     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e89-d.3.900     Document Type: Conference Paper

References (28)

1. F. Jelinek, L. Bahl, and R. Mercer, "Design of a linguistic statistical decoder for the recognition of continuous speech," IEEE Trans. Inf. Theory, vol.21, no.3, pp.250-256, 1975.
2. F. Jelinek, "Continuous speech recognition by statistical methods," Proc. IEEE, vol.64, pp.532-556, 1976.
3. J. Odell, The Use of Context in Large Vocabulary Speech Recognition, Ph.D. Thesis, University of Cambridge, 1995.
4. S. Young, G. Evermann, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland, The HTK Book Version 3.0, Cambridge University, 2000.
5. C.J. Leggetter and P.C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol.9, pp.171-185, April 1995.
6. P. Woodland and D. Povey, "Large scale discriminative training for speech recognition," Proc. ITW ASR, ISCA, 2000.
7. J. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," IEEE ASRU Workshop, pp.347-352, 1997.
8. Y. Ephraim and L.R. Rabiner, "On the relations between modeling approaches for information sources," IEEE Trans. Inf. Theory, vol.36, no.2, pp.372-380, March 1990.
9. W. Byrne, "Information geometry and maximum likelihood criteria," Conference on Information Sciences and Systems, Princeton, NJ, 1996.
10. A. Stolcke, Y. Konig, and M. Weintraub, "Explicit word error minimization in N-Best list rescoring," Proc. European Conference on Speech Technology, pp. 163-166, Rhodes, Greece, 1997.
11. V. Goel, S. Kumar, and W. Byrne, "Confidence based lattice segmentation and minimum Bayes-risk decoding of lattice segments," Proc. European Conference on Speech Technology, Aalborg, Denmark, 2001.
12. S. Kumar and W. Byrne, "Risk based lattice cutting for segmental minimum Bayes-risk decoding," ICSLP 2002, pp.373-376, Denver, CO, USA, 2002.
13. V. Goel and W. Byrne, "Minimum Bayes-risk automatic speech recognition," Comput. Speech Lang., vol.14, no.2, pp. 115-135, 2000.
14. V. Goel and W. Byrne, "Minimum Bayes-risk automatic speech recognition," in Pattern Recognition in Speech and Language Processing, ed. W. Chou and B.H. Juang, CRC Press, 2003.
15. V. Goel, S. Kumar, and W. Byrne, "Segmental minimum Bayes-risk decoding for automatic speech recognition," IEEE Trans. Speech Audio Process., vol.12, no.3, pp.234-249, May 2004.
16. V. Doumpiotis and W. Byrne, "Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition," Speech Commun., no.2, pp. 142-160, 2005.
17. V. Venkataramani, S. Chakrabartty, and W. Byrne, "Ginisupport vector machines for segmental minimum Bayes risk decoding of continuous speech," Comput. Speech Lang., 'Accepted. To appear'.
18. V. Venkataramani and W. Byrne, "Lattice segmentation and support vector machines for large vocabulary continuous speech recognition," Proc. ICASSP, pp.817-820, 2005.
19. W. Byrne, D. Doermann, M. Franz, S. Gustman, J. Hajic, D. Oard, M. Picheny, J. Psutka, B. Ramabhadran, D. Soergel, T. Ward, and W.-J. Zhu, "Automatic recognition of spontaneous speech for access to multilingual oral history archives," IEEE Trans. Speech Audio Process., vol.12, no.4, pp.420-435, July 2004.
20. V. Doumpiotis, S. Tsakalidis, and W. Byrne, "Lattice segmentation and minimum Bayes risk discriminative training," Proc. European Conference on Speech Technology, 2003.
21. N. Smith and M. Gales, "Using SVMs and discriminative models for speech recognition," Proc. ICASSP, pp.77-80, 2002.
22. V. Venkataramani and W. Byrne, "Support vector machines for segmental minimum Bayes risk decoding of continuous speech," ASRU, 2003.
23. S. Chakrabartty and G. Cauwenberghs, "Forward decoding kernel machines: A hybrid HMM/SVM approach to sequence recognition," Proc. SVM 2002, Lecture Notes in Computer Science, MIT Press, 2002. Toolkit: http://bach.ece.jhu.edu/svm/ginisvm/
24. D. Pallett, W. Fisher, and J. Fiscus, "Tools for the analysis of benchmark speech recognition tests.," Proc. ICASSP, pp.97-100, 1990.
25. J. Kaiser, B. Horvat, and Z. Kacic, "Overall risk criterion estimation of hidden Markov model parameters," Speech Commun., vol.38, no.3-4, pp.383-398, 2002.
26. P.S. Gopalakrishnan, D. Kanevsky, A. Nádas, and D. Nahamoo, "An inequality for rational functions with applications to some statistical estimation problems," IEEE Trans. Inf. Theory, vol.37, no.1, pp. 107-113, Jan. 1991.
27. B.H. Juang and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Trans. Speech Audio Process., vol.40, no. 12, pp.3043-3054, Dec. 1992.
28. Y. Normandin, "Maximum mutual information estimation of hidden Markov models," in Automatic Speech and Speaker Recognition, ed. C.H. Lee, F.K. Soong, and K.K. Paliwal, pp.57-82, Kluwer Academic Publishers, 1996.