Minimum hypothesis phone error as a decoding method for speech recognition

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 76-79

  Xu, Haihua ^a   Povey, Daniel ^b   Zhu, Jie ^a   Wu, Guanyong ^a  

^a SHANGHAI JIAO TONG UNIVERSITY   (China)

^b MICROSOFT RESEARCH   (United States)

Author keywords

Confusion networks; Lattice rescoring; Minimum bayes risk (MBR); MPE; Speech recognition

Indexed keywords

DECODING METHODS; DISCRIMINATIVE TRAINING; LATTICE RESCORING; MAXIMUM A POSTERIORI; MINIMUM BAYES RISK; MINIMUM PHONE ERROR; SENTENCE ERRORS; WORD ERROR RATE;

ACOUSTIC SIGNAL PROCESSING; DECODING; RISK PERCEPTION; SPEECH COMMUNICATION; TELEPHONE SETS;

SPEECH RECOGNITION;

EID: 70450191546     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. L. Mangu, E. Brill, A. Stolcke, "Findng consensus in speech recognition: word error minimization and other applications of confusion networks", Computer Speech and Language 14 (4),291-294,2000.
2. G. Evermann, P.C. Woodland, "Posterior probability decoding, confidence estimation and system combination", Proc. Speech Transcription Workshop, 2000.
3. F. Wessel, R. Schlüter, H. Ney," Explicit word error minimization using word hypothesis posterior probabilities", in Proc. ICASSP'01, Salt Lake City, UT,pp.33-36,2001.
4. D. Povey, P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training", in Proceedings of the ICASSP'02, Vol. 1, Florida, USA, pp. 105-108,2002.
5. D. Povey, "Discriminative training for large vocabulary speech recognition", Ph.D. thesis, Cambridge University, 2004.
6. D. Povey, K. Brian, "Evaluation of proposed modifications to MPE for large scale discriminative training", Proc. ICASSP'07, Vol. 4, Hawaii, USA,pp. 321-324,2007.
7. A. Stolcke, Y. König, M. Weintraub, "Explicit word error minimization in N-best list rescoring", in Procceedings of the 5th European Conference on Speech Communication and Technology, Vol. 1, Rhodes, Greece, pp. 163-166,1997.
8. H. Xu, J. Zhu, "Towards more efficient and accurate methods for mandarin LVCSR discriminative training", in Proc. ICME'08, Hannover, Germany, pp. 981-984,2008.
9. H. Xu, J. Zhu, G. Wu, "An efficient multistage rover method for automatic speech recognition", in Proc. ICME'09, 2009.
10. D. Povey, D. Kanevsky, et al., "Boosted MMI for model and feature-space discriminative training", Proc. ICASSP'08, pp. 4057-4060, 2008.
11. S. Ortmanns, H. Ney, "A word graph algorithm for large vocabulary continuous speech recognition", Computer Speech and Language 11 (1), 43-72, 1997.
12. S. Young, et al., "The HTK Book, 3rd Edition", Cambridge University, 2006.