Minimum Bayes Risk decoding and system combination based on a recursion for edit distance

Computer Speech and Language

Volumn 25, Issue 4, 2011, Pages 802-828

  Xu, Haihua ^a   Povey, Daniel ^b   Mangu, Lidia ^c   Zhu, Jie ^a  

^a SHANGHAI JIAO TONG UNIVERSITY   (China)

^b MICROSOFT RESEARCH   (United States)

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

Author keywords

Minimum Bayes Risk decoding; Speech recognition

Indexed keywords

BAYES RISK; CONSENSUS METHODS; EDIT DISTANCE; MINIMUM BAYES RISK; MINIMUM BAYES RISK DECODING; RECURSIONS; SYSTEM COMBINATION; THEORETICAL BASIS;

ALGORITHMS; DECODING;

SPEECH RECOGNITION;

EID: 79953250475     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2011.03.001     Document Type: Article

References (27)

1. C. Allauzen, M. Riley, J. Schalkwyk, W. Skut, and M. Mohri Openfst: a general and efficient weighted finite-state transducer library Proc. CIAA 2007 11 23
2. E. Chang, Y. Shi, J. Zhou, and C. Huang Speech lab in a box: a mandarin speech toolbox to jumpstart speech related research Proc. Interspeech 2001
3. G. Evermann, and P. Woodland Posterior probability decoding, confidence estimation and system combination Proc. Speech Transcription Workshop 2000
4. J.G. Fiscus A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) ASRU 1997
5. V. Goel, and W. Byrne Minimum Bayes-risk automatic speech recognition Computer Speech and Language 2 2000 14
6. Graeme Blackwood, Adri de Gispert, and William Byrne Efficient path counting transducers for minimum Bayes-risk decoding of statistical machine translation lattices Proc. ACL 2010
7. G. Heigold, W. Macherey, R. Schlüter, and H. Ney Minimum exact word error training Proc. ASRU 2005
8. H. Hermansky Perceptual linear predictive (PLP) analysis of speech Journal of the Acoustical Society of America 87 1990 1738 1752 (Pubitemid 20256470)
9. B. Hoffmeister, R. Schlüter, and H. Ney Bayes risk approximations using time overlap with an application to system combination Proc. Interspeech 2009
10. S. Kirpatrick, C. Gelatt, and M. Vecchi Jr. Optimization by simulated annealing Science 220 May 1983 671 680
11. V.I. Levenshtein Binary codes capable of correcting deletions, insertions, and reversals Soviet Physics Doklady 1966 10
12. L. Mangu, E. Brill, and A. Stolcke Finding Consensus in speech recognition: word error minimization and other applications of confusion networks Computer Speech and Language 4 2000 14
13. M. Mohri, F. Pereira, and M. Riley Weighted finite-state transducers in speech recognition Computer Speech and Language 20 1 2002 69 88
14. K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu Bleu: a method for automatic evaluation of machine translation Proc. ACL 2002 311 318
15. Povey, D., Burget, L., Agarwal, M., Akyazi, P., Kai, F., Ghoshal, A., Glembek, O., Goel, N.K., Karafiát, M., Rastrow, A., Rose, R.C., Schwarz, P., Thomas, S., 2011. The subspace Gaussian Mixture Model - a structured model for speech recognition. Computer Speech and Language 25 (2).
16. D. Povey, L. Burget, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N.K. Goel, M. Karafiát, A. Rastrow, R.C. Rose, P. Schwarz, and S. Thomas Subspace Gaussian mixture models for speech recognition Proc. ICASSP 2010
17. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah Boosted MMI for feature and model space discriminative training Proc. ICASSP 2008
18. D. Povey, and P. Woodland Minimum phone error and i-smoothing for improved discriminative training Proc. ICASSP 2002
19. Y. Qian, S. Lin, Y. Zhang, Y. Liu, H. Liu, and Q. Liu An introduction to corpora resources of 863 program for Chinese language processing and human-machine interaction Proc. ALR-04, affiliated to IJCNLP 2004
20. G. Saon, H. Soltau, U. Chaudhari, S. Chu, B. Kingsbury, H.-K. Kuo, L. Mangu, and D. Povey The IBM, GALE Arabic speech transcription system Proc. ICASSP 2008
21. A. Stolcke, Y. König, and M. Weintraub Explicit word error minimization in N-best list rescoring 5th European Conf. on Speech Comm. and Technology 1997 163 166
22. Y. Tian, J. Zhou, H. Lin, and H. Jiang Tree-based covariance modeling of hidden markov models IEEE Transaction on Audio, Speech and Language Processing 14 6 2006 2134 2146
23. F.R. Wessel, and H.N. Schlüter Explicit word error minimization using word hypothesis posterior probabilities Proc. ICASSP 2001
24. H. Xu, D. Povey, L. Mangu, and J. Xhu An improved consensus-like method for minimum Bayes risk decoding and lattice combination Proc. ICASSP 2010
25. H. Xu, D. Povey, J. Zhu, and G. Wu Minimum hypothesis phone error as a decoding method for speech recognition Proc. Interspeech 2009
26. S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland The HTK Book (for version 3.4) 2009 Cambridge University Engineering Department
27. J. Zhang, F. Zheng, J. Li, C. Luo, and G. Zhang Improved context-dependent acoustic modeling for continuous Chinese speech recognition Proc. Interspeech 2001