Minimum bayes-risk methods in automatic speech recognition

Pattern Recognition in Speech and Language Processing

Volumn , Issue , 2003, Pages 51-80

  Goel, Vaibhava ^a   Byrne, William ^b  

^a IBM T J WATSON RESEARCH CENTER   (United States)

^b Johns Hopkins University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 85009178203     PISSN: None     EISSN: None     Source Type: Book    
DOI: 10.1201/9780203010525     Document Type: Chapter

References (40)

1. P. J. Bickel and K. A. Doksum. Mathematical Statistics: Basic Ideas and Selected topics. Holden-Day Inc., Oakland, CA, 1977.
2. W. Byrne, P Beyerlein, J. Huerta, S. Khudanpur, B. Marthi, J. Morgan, N. Pe-terek, J. Picone, D. Vergyri, and W. Wang. Towards language independent acoustic modeling. In IEEE Conference on Acoustics, Speech, and Signal Processing, pages 1029-1032, Istanbul, Turkey, 2000.
3. th Hub-5 Conversational Speech Recognition Workshop, 1998. Available at www.nist.gov/speech/hub4.98.
4. G. Evermann and P Woodland. Posterior Probability Decoding, Confidence Estimation and System Combination. In In Proceedings of the NIST and NSA Speech Transcription Workshop, College Park, MD, 2000.
5. J. Fiscus. A Post-processing System to Yield Reduced Word Error Rates: Recognizer Output Voting Error Reduction (ROVER). InIEEE Workshop on Automatic Speech Recognition and Understanding, pages 347-354,1997.
6. Radu Florian and David Yarowsky. Dynamic Nonlocal Language Modeling via Hierarchical Topic-Based Adaptation. In ACL99, pages 167-174,1999.
7. J. J. Godfrey, E. C. Holliman, and J. McDaniel. Switchboard: Telephone Speech Corpus for Research and Development. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 517-520, San Francisco, CA, 1992.
8. V. Goel. Word List With Content Word Marks, 1999. Available at http://www.clsp.jhu.edu/people/vgoel.
9. V. Goel. Minimum Bayes-Risk Automatic Speech Recognition. Ph. D.Dissertation, Johns Hopkins University, Baltimore, MD, 2001.
10. V. Goel and W. Byrne. Task Dependent Loss Functions in Speech Recognition:,4 Search over Recognition Lattices. In Eurospeech-99, pages 1243-1246, Budapest, Hungary, 1999.
11. V. Goel and W. Byrne. Applications of Minimum Bayes-Risk Decoding to LVCSR. In In Proceedings of the NIST and NSA Speech Transcription Workshop, College Park, MD, 2000.
12. V. Goel and W. Byrne. Minimum Bayes-Risk Automatic Speech Recognition. Computer Speech and Language, 14(2):115-135,2000.
13. V. Goel and W. Byrne. Recognizer Output Voting and DMC in Minimum Bayes-Risk Framework. In Research Notes No. 40, Center for Language and Speech Processing, 2000
14. V. Goel, W. Byrne, and S. Khudanpur. LVCSR Rescoring With Modihed Loss Functions: A Decision Theoretic Perspective. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 425-428,1998.
15. th International Conference on Spoken Language Processing, volume 3, pages 139-142, Beijing, China, 2000.
16. P S. Gopalakrishnan, L. R. Bahl, and R. L. Mercer A Tree Search Strategy for Large Vocabulary Continuous Speech Recognition. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 572-575,1995.
17. P E. Hart, N. J. Nilsson, and B. Raphael. A Formal Basis for the Heuristic Determination of Minimum Cost Paths. IEEE Transactions on Systems Science and Cybernetics, SSC-4(2):100-107,1968.
18. P E. Hart, N. J. Nilsson, and B. Raphael. Correction to ‘A Formal Basis for the Heuristic Determination of minimum Cost Paths’. SIGARTNewsletter, 37:28-29, 1972.
19. F. Jelinek. A Fast Sequential Decoding Algorithm Using a Stack. IBM Journal of Research Development, 13:675-685,1969.
20. F Jelinek Statistical Methods for Speech Recognition The MIT Press, Cambridge, Massachusetts, 1997
21. Proceedings of the 1997 Large Vocabulary Continuous Speech Recognition Workshop, 1997. Available at http://www.clsp.jhu.edu/ws97.
22. B-H. Juang and S. Katagiri. Discriminative Learning for MinimumError Clas-sihcation. IEEE Transactions on Signal Processing, SP-40(12):3043-3054, 1992
23. th International Conference on Spoken Language Processing, volume 2, pages 887-890, Beijing, China, 2000.
24. T. Kawahara, C-H. Lee, and B-H. Juang. Combining Key Phrase Detection and Subword Based Verihcation for Flexible Speech Understanding. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 193-196, 1997.
25. M. W. Koo, C-H. Lee, and B-H. Juang. A New Hybrid Decoding Algorithm for Speech Recognition and Utterance Verification. In 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, pages 303-310,1997.
26. V. I. Levenshtein. Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Phys. Dokl, 10:707-710,1966.
27. L. Mangu, E. Brill, and A. Stolcke. Finding Consensus Among Words: Lattice-Based Word Error Minimization. In Eurospeech-99, pages 495-498, Budapest, Hungary, 1999.
28. A. Martin, J. Fiscus, M. Przybocki, and B. Fisher. 1998 Hub-5 Workshop: Information Retrieval. In 9th Hub-5 Conversational Speech Recognition Workshop, 1998.
29. A. Martin, J. Fiscus, M. Przybocki, and B. Fisher. 1998 Hub-5 Workshop: Weighted Word Results. In 9th Hub-5 Conversational Speech Recognition Workshop, 1998.
30. K. Na, B. Jeon, D. Chang, S. Chae, and S. Ann. Discriminative Training of Hidden Markov Models Using Overall Risk Criterion and Reduced Gradient Method. In Eurospeech-95, pages 97-100, Madrid, Spain, 1995.
31. A. Nadas. A Decision Theoretic Formulation of the Training Problem in Speech Recognition and a Comparison of Training by Unconditional Versus Conditional Maximum Likelihood. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-31(4):814-817,1983.
32. A. Nadas. Optimal Solution of a Training Problem in Speech Recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-33(1):326-329,1985.
33. D. B. Paul. An Efficient,4 Stack Decoder Algorithm for Continuous Speech Recognition with a Stochastic Language Model. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 25-28,1992.
34. E. Ristad and P. Yianilos. Learning String Edit Distance. IEEE Trans. PAMI, 20(5):522-532,1998.
35. R. C. Rose and D. B. Paul. A Hidden Markov Model Based Keyword Recognition System. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 129-132,1990.
36. A. Stolcke, Y. Konig, and M. Weintraub. Explicit Word Error Minimization in N-Best List Rescoring. In Eurospeech-97, volume 1, pages 163-165, Rhodes, Greece, 1997.
37. V. Vapnik. Estimation of Dependences Based on Empirical Data. SpringerVerlag, New York, 1982.
38. F. Wessel, R. Schluter, and H. Ney. Using Posterior Word Probabilities For Improved Speech Recognition. In IEEE Conference on Acoustics, Speech, and Signal Processing, volume 3, pages 1587-1590, Istanbul, Turkey, 2000.
39. J G Wilpon, L R Rabiner, C-H Lee, and E R Goldman Automatic Recognition of Keywords in Unconstrained Speech Using Hidden Markov ModelsIEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-38(11):1870-1878,1990.
40. S. Young. HTK 2.1. Entropic Cambridge Research Laboratory Ltd., Cambridge, UK, 1997.