An improved consensus-like method for minimum bayes risk decoding and lattice combination

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

Volumn , Issue , 2010, Pages 4938-4941

  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

Confusion network; Consensus; Lattice rescoring; Minimum bayes risk (MBR); Speech recognition

Indexed keywords

DECODING; SIGNAL PROCESSING;

BAYES RISK; CONFUSION NETWORKS; CONSENSUS; LATTICE RESCORING; LATTICE-BASED; MINIMUM BAYE RISK; MINIMUM BAYES RISK; NETWORK DECODING; SYSTEM COMBINATION; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 78049383565     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495100     Document Type: Conference Paper

References (13)

1. V. I. Levenshtein, "Binary codes capable of correcting deletions, insertions, and reversals," Soviet Physics Doklady, vol. 10, 1966.
2. 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, vol. 14, no. 4, 2000.
3. Y. König A. Stolcke and M.Weintraub, "Explicit word error minimization in N-best list rescoring," in 5th European Conf. on Speech Comm. and Technology, 1997, pp. 163-166.
4. V. Goel and W. Byrne, "Minimum Bayes-risk automatic speech recognition," Computer Speech and Language, vol. 14, no. 2, 2000.
5. G. Evermann and P.C.Woodland, "Posterior probability decoding, confidence estimation and system combination," in Speech Transcription Workshop, 2000.
6. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER)," in ASRU, 1997.
7. F.Wessel, R. Schlüter, H. Ney, "Explicit word error minimization using word hypothesis posterior probabilities," in ICASSP, 2001.
8. Xu H., Povey D., Zhu J. and Wu G., "Minimum Hypothesis Phone Error as a Decoding Method for Speech Recognition," in Interspeech, 2009.
9. Björn Hoffmeister, Ralf Schlüter, and Hermann Ney, "Bayes Risk Approximations Using Time Overlap with an Application to System Combination," in Interspeech, 2009.
10. Heigold G.,Macherey W., Schlüter R., Ney H., "Minimum Exact Word Error Training," in ASRU, 2005.
11. Povey D. and Woodland P.C., "Minimum Phone Error and I-smoothing for Improved Discriminative Training," in ICASSP, 2002.
12. Povey D., Kanevsky D., Kingsbury B., Ramabhadran B., Saon G. and Visweswariah K., "Boosted MMI for Feature and Model Space Discriminative Training," in ICASSP, 2008.
13. A. Stolcke, "SRILM - An Extensible Language Modeling Toolkit," in ICSLP, 2002.