Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition

Speech Communication

Volumn 48, Issue 2, 2006, Pages 142-160

  Doumpiotis, Vlasios ^a,c   Byrne, William ^a,b  

^a Johns Hopkins University   (United States)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^c EScription Inc   (United States)

Author keywords

Acoustic modeling; Discriminative training; Large vocabulary speech recognition; Lattice segmentation; Maximum mutual information (MMI) estimation; Minimum Bayes risk decoding; Risk minimization

Indexed keywords

ALGORITHMS; DECODING; ESTIMATION; INFORMATION ANALYSIS; MATHEMATICAL MODELS; RISK ASSESSMENT; VOCABULARY CONTROL;

ACOUSTIC MODELING; DISCRIMINATIVE TRAINING; LARGE VOCABULARY SPEECH RECOGNITION; LATTICE SEGMENTATION; MAXIMUM MUTUAL INFORMATION (MMI) ESTIMATION; MINIMUM BAYES RISK DECODING; RISK MINIMIZATION;

SPEECH RECOGNITION;

EID: 29444447644     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2005.07.002     Document Type: Article

References (23)

1. Byrne, W., 2001. The JHU March 2001 Hub-5 conversational speech transcription system. In: Proc. NIST LVCSR Workshop. NIST.
2. Byrne, W., Doermann, D., Franz, M., Gustman, S., Hajič, J., Card, D., Picheny, M., Psutka, J., Ramabhadran, B., Soergel, D., Ward, T., Zhu, W.-J., 2004. Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Trans. Speech Audio Process., Special Issue Spontaneous Speech Process.
3. V. Goel, and W. Byrne Minimum Bayes-risk automatic speech recognition Comput. Speech Lang. 14 2 2000 115 135
4. Goel, V., Kumar, S., Byrne, W., 2001. Confidence based lattice segmentation and minimum Bayes-risk decoding of lattice segments. In: Euro. Conf. on Speech Communication and Technology, Vol. 4. Aalborg, Denmark, pp. 2569-2572.
5. V. Goel, S. Kumar, and W. Byrne Segmental minimum Bayes-risk decoding for automatic speech recognition IEEE Trans. Speech Audio Process 2004
6. 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 37 1 1991 107 113
7. H. Hermansky Perceptual linear predictive (PLP) analysis of speech J. Acoust. Soc. Amer. 87 4 1990 1738 1752
8. B.-H. Juang, and S. Katagiri Discriminative learning for minimum error classification IEEE Trans. Signal Process. 40 12 1992 3043 3054
9. Kaiser, J., Horvat, B., Kacic, Z., 2000. A novel loss function for the overall risk criterion based discriminative training of HMM models. In: ICSLP. Beijing, China.
10. J. Kaiser, B. Horvat, and Z. Kacic Overall risk criterion estimation of hidden Markov model parameters Speech Communication 38 3-4 2002 383 398
11. Kumar, S., Byrne, W., 2002. Risk based lattice cutting for segmental minimum Bayes-risk decoding. In: ICSLP 2002. Denver, CO, USA, pp. 373-376.
12. Martin, A., Fiscus, J., Przybocki, M., Fisher, B., 1998. The evaluation: Word error rates and confidence analysis. In: Hub-5 Workshop. NIST, Linthicurn Heights, Maryland. Available from: < http://www.nist.gov/speech/tests/ctr/ hub5e.98/hub5e-98.htm>.
13. Martin, A., Przybocki, M., Fiscus, J., Pallett, D., 2000. The 2000 NIST evaluation for recognition of conversational speech over the telephone. In: Proc. Speech Transcription Workshop. NIST.
14. Mohri, M., Pereira, F., Riley, M., 2001. ATT General-purpose finite-state machine software tools. Available from: < http://www.research.att.com/sw/ tools/fsm/>.
15. Mohri, M., Riley, M., 1999. Integrated context-dependent networks in very large vocabulary speech recognition. In: Euro. Conf. on Speech Communication and Technology.
16. Noel, M., 1997. Alphadigits. Tech. rep., Center for Spoken Language Understanding, Oregon Graduate Institute of Science and Technology, Portland, OR. Available from: < http/www.cse.ogi.edu/CSLU/corpora/alphadigit>.
17. Y. Normandin Maximum mutual information estimation of hidden Markov models C.-H. Lee F.K. Soong K.K. Paliwal Automatic Speech and Speaker Recognition: Advanced Topics 1996 Kluwer 57 81 (Chapter 3)
18. Pallett, D., Fisher, W., Fiscus., J., 1990. Tools for the analysis of benchmark speech recognition tests. In: Internat. Conf. on Acoustics, Speech, and Signal Processing, Vol. 1. pp. 97-100.
19. D. Sankoff J. Kruskal Time Warps, String Edits, ard Macro-molecules: The Theory and Practice of Sequence Comparison 1983 Addison-Wesley
20. Stolcke, A., Bratt, H., Butzberger, J., Franco. H., Rao Gadde, V.R., Plauche, M., Richey, C., Shriberg, E., Sonmez, K., Weng, F., Zheng, J., 2000. The SRI March 200 Hub-5 conversational speech transcription system. In: Proc. Speech Transcription Workshop. NIST.
21. Stolcke, A., Konig, Y., Weintraub, M., 1997. Explicit word error minimization in n-best list rescoring. In: Eurospeech. Rhodes, Greece.
22. Woodland, P.C., Povey, D., 2000. Large scale discriminative training for speech recognition. In: Proc. Tutorial and Research Workshop on Automatic Speech Recognition. ISCA.
23. Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland, P., 2000. The HTK Book, Version 3.0.