Segmental minimum Bayes-risk decoding for automatic speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 12, Issue 3, 2004, Pages 234-249

  Goel, Vaibhava ^a   Kumar, Shankar ^b   Byrne, William ^b  

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

^b Johns Hopkins University   (United States)

Author keywords

ASR system combination; Extended ROVER; Lattice cutting; Minimum Bayes risk decoding; Segmental minimum Bayes risk decoding

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL COMPLEXITY; DECODING; ERROR ANALYSIS; MARKOV PROCESSES; PROBABILITY; SPEECH CODING;

AUTOMATIC SPEECH RECOGNITION (ASR) SYSTEMS; EXTENDED-ROVER; LATTICE CUTTING; SEGMENTAL MINIMUM BAYES RISK DECODING;

SPEECH RECOGNITION;

EID: 2442562479     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2004.825678     Document Type: Article

References (27)

1. V. I. Levenshtein, "Binary codes capable of correcting spurious insertions and deletions of ones," Probl. Inform. Transmits., vol. 1, no. 1, pp. 8-17, 1965.
2. P. J. Bickel and K. A. Doksum, Mathematical Statistics: Basic Ideas and Selected Topics. Oakland, CA: Holden-Day, 1977.
3. V. Goel, S. Kumar, and W. Byrne, "Segmentai minimum Bayes-risk ASR voting strategies," in Proc. ICSLP 2000, vol. 3, Beijing, China, 2000, pp. 139-142.
4. V. Goel and W. Byrne, "Recognizer output voting and DMC in minimum Bayes-risk framework," Res. Notes no. 40, Center for Language and Speech Processing, 2000.
5. J. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Proc. ASRU 1997, 1997, pp. 347-354.
6. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus in speech recognition: Word error minimization and other applications of confusion networks," Comput. Speech Lang., vol. 14, no. 4, pp. 373-400, 2000.
7. G. Evermann and P. Woodland, "Posterior probability decoding, confidence estimation and system combination," in Proc. NIST Speech Transcription Workshop, College Park, MD, 2000.
8. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Comput. Speech Lang., vol. 16, no. 1, pp. 69-88, 2002.
9. _, (2001) AT&T General-Purpose Finite-State Machine Software Tools. [Online]. Available: http://www.research.att.com/sw/tools/fsm/
10. A. Stolcke, Y. Konig, and M. Weintraub, "Explicit word error minimization in N-best list rescoring," in Eurospeech 1997, vol. 1, Rhodes, Greece, 1997, pp. 163-165.
11. V. Goel and W. Byrne, "Minimum Bayes-risk automatic speech recognition," Comput. Speech Lang., vol. 14, no. 2, pp. 115-135, 2000.
12. S. Kumar and W. Byrne, "Risk based lattice cutting for segmental minimum Bayes-risk decoding," in ICSLP 2002, Denver, CO, 2002, pp. 373-376.
13. M. Mohri, F. Pereira, and M. Riley, "The design principles of a weighted finite-state transducer library," Theor. Comput. Sci., vol. 231, no. 1, pp. 17-32, 2000.
14. R. E. Bellman, Dynamic Programming. Princeton, NJ: Princeton Univ. Press, 1957.
15. D. Sankhoff and J. B. Kruskal, Time Warps, String Edits and Macromolecules: The Theory and Practice of String Comparison. Reading, MA: Addison-Wesley, 1983.
16. M. Mohri, "Edit-distance of weighted automata," in Proc. 7th Int. Conf. Implementation and Application of Automata, J.-M. Champarnaud and D. Maurel, Eds., 2002.
17. V. Goel, S. Kumar, and W. Byrne, "Confidence based lattice segmentation and minimum Bayes-risk decoding," in Proc. Eurospeech 2001, vol. 4, Aalborg, Denmark, 2001, pp. 2569-2572.
18. F. Wessel, R. Schlueter, and H. Ney, "Explicit word error minimization using word hypothesis posterior probabilities," in Proc. ICASSP-01, Salt Lake City, UT, 2001, pp. 33-36.
19. F. Wessel, K. Macherey, and R. Schlueter, "Using word probabilities as confidence measures," in Proc. ICASSP-98, Seattle, WA, 1998, pp. 225-228.
20. A. Stolcke, H. Bratt, J. Butzberger, H. Franco, V. R. R. Gadde, M. Plauche, C. Richey, E. Shriberg, K. Sonmez, F. Weng, and J. Zheng, "The SRI March 2000 Hub-5 conversational speech transcription system," in Proc. NIST Speech Transcription Workshop, College Park, MD, 2000.
21. S. Young et al., The HTK Book, 3.0 ed., 2000.
22. W. Byrne, A. Gunawardana, S. Kumar, and V. Venkataramani, "The JHU March 2001 Hub-5 conversational speech transcription system," in Proc. NIST LVCSR Workshop, 2001.
23. W. Byrne, P. Beyerlein, J. Huerta, S. Khudanpur, B. Marthi, J. Morgan, N. Peterek, J. Picone, D. Vergyri, and W. Wang, "Toward language independent acoustic modeling," in Proc. IEEE Conf. Acoustics, Speech, and Signal Processing, Istanbul, Turkey, 2000, pp. 1029-1032.
24. Voice of America Broadcast News Czech Transcript Corpus, by J. Psutka et al. (2000). [Online]. Available: http://www.ldc.upenn.edu/Catalog/CatalogEntry. jsp?catalogId=LDC2000T53
25. W. Byrne, V. Doumpiotis, S. Kumar, S. Tsakalidis, and V. Venkataramani, "The JHU 2002 large vocabulary speech recognition system," in Proc. NISTRT-02 Workshop, 2002.
26. S. Tsakalidis, V. Doumpiotis, and W. Byrne, "Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation," in Proc. ICSLP 2002, Denver, CO, 2002, pp. 2585-2588.
27. V. Doumpiotis, S. Tsakalidis, and W. Byrne, "Lattice segmentation and minimum Bayes-risk discriminative training," in Proc. Eurospeech 2003, Geneva, Switzerland, 2003.