Beam search pruning in speech recognition using a posterior probability-based confidence measure

Speech Communication

Volumn 42, Issue 3-4, 2004, Pages 409-428

  Abdou, Sherif ^a   Scordilis, Michael S ^b  

^a BBN TECHNOLOGIES   (United States)

^b UNIVERSITY OF MIAMI   (United States)

Author keywords

Confidence measure; Discriminative training; Pruning; Speech recognition

Indexed keywords

DECODING; INFORMATION ANALYSIS; MAXIMUM LIKELIHOOD ESTIMATION; PERSONNEL TRAINING; SEARCH ENGINES;

CONFIDENCE MEASURES; DISCRIMINATIVE TRAINING; PRUNING;

SPEECH RECOGNITION;

EID: 1842475644     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2003.11.002     Document Type: Article

References (41)

1. Amtrup, J.W., Heine, H., Jost, U., 1997. What's in a word graph? Evaluation and enhancement of word lattices. In: Proc. Eurospeech 1997, Rhodes, Greece, pp. 2663-2666.
2. Bennett, C., Rudnicky, A.I., 2002. The Carnegie Mellon COMMUNICATOR corpus. In: Internat. Conf. on Spoken Language Process., ICSLP'02, Beijing, China, pp. 341-344.
3. Bocchieri, E., 1993. Vector quantization for the efficient computation of continuous density likelihoods. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., Vol. 1, pp. 692-695.
4. Bourlard H., Morgan N. Connectionist Speech Recognition: A Hybrid Approach. 1994;Kluwer Academic Publishers, New York.
5. Bouwman, G., Boves, L., Koolwaaij, J., 2000. Weighting phone confidence measures for automatic speech recognition. In: Proc. COST Action 249, Ghent, pp. 59-62.
6. Brushtein D. Robust parametric modeling of durations in hidden Markov models. IEEE Trans. Speech Audio Process. 4(3):1996;240-242.
7. Chase, L.L., 1997a. Error-responsive feedback mechanisms for speech recognizers. Ph.D. Thesis, Carnegie Mellon University, USA.
8. Chase, L., 1997b. Word and acoustic confidence annotation for large vocabulary speech recognition. In: Proc. Eurospeech 1997, Rhodes, Greece, pp. 815-818.
9. Digalakis V.V., Monaco P., Murveit H. Genones: generalized mixture tying in continuous hidden Markov model based speech recognition. IEEE Trans. Speech Audio Process. 4(4):1996;281-289.
10. Duda R.O., Hart P.E. Pattern classification and scene analysis. 1973;John Wiley and Sons, New York.
11. Finke, M., Zeppenfeld, T., Maier, M., Mayfield, L., Ries, K., Zhan, P., Lafferty, J., Waibel, A., 1996. DARPA: Switchboard April 1996 Evaluation Report, pp. 29-35.
12. Gillick, L., Ito, Y., Young, J., 1997. A probabilistic approach to confidence estimation and evaluation. In: Proc. IEEE Int. Conf. Acoust., Speech Signal Process., pp. 879-883.
13. Graff, D., 1996. The 1996 Broadcast News speech and language-model corpus. In: Proc. ARPA Workshop on Human Lang. Technol., pp. 50-59.
14. Halberstadt, A.K., 1998. Heterogeneous acoustic measurements and multiple classifiers for speech recognition, Ph.D. Thesis, M.I.T. Department of Electrical Engineering and Computer Science, November 1998.
15. Herman, S.M., Sukkar, R.A., 1997. Variable threshold vector quantization for reduced continuous density likelihood computation in speech recognition. In: Proc. 1997 IEEE Workshop Automat. Speech Recognition Understanding, pp. 331-337.
16. Hernandez, G.A., 2000. Confidence measures for speech recognition and utterance verification, Ph.D. Thesis, University Politecnica de Catalunya, Spain.
17. Huang, X.D., Lee, K.F., Hon, H.W., 1990. On semi-continuous hidden Markov models. In: Proc. IEEE Internat. Conf. Acoust., Speech and Signal Process., pp. 689-692.
18. Hwang, M.Y., Huang, X., Alleva, F., 1993. Predicting unseen triphones with senones. In: Proc. IEEE Internat. Conf. Acoust., Speech Signal Process., Minneapolis, pp. 311-314.
19. Jiang, H., Soong, F., Lee, C.-H., 2001. A data selection strategy for utterance verification in continuous speech recognition. In: Proc. Eurospeech 2001, Aalborg, Denmark, pp. 2573-2576.
20. Kamppari, S., 1999. Acoustic confidence scoring for speech understanding systems, Master's Thesis, Massachusetts Institute of Technology, 1999.
21. Koo, M.-W., Lee, C.-H., Huang, B.-H., 1998. A new decoder based on a generalized confidence score. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., pp. 213-216.
22. Lee, C.-H., 2001. Statistical confidence measures and their applications. In: Proc. Internat. Conf. on Speech Process., ICSP 2001, Dajeong, Korea, pp. 356-359.
23. Lleida, E., Rose, R.C., 1996. Efficient decoding and training procedures for utterance verification in continuous speech recognition. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., Vol. 1, pp. 507-510.
24. Mak, B., Barnard, E., 1996. Phone clustering using the Bhattacharyya distance. Proc. Internat. Conf. on Spoken Language Process., ICSLP'96, Vol. 4, pp. 2005-2008.
25. Mangu, L., Brill, E., Stolcke, A., 1999. Finding consensus among words: lattice-based word error minimization. In: Proc. Eurospeech 1999, Budapest 1999, pp. 495-498.
26. Ney H., Mergel D., Noll A., Paesler A. Data-driven search organization for continuous speech recognitions. IEEE Trans. Signal Process. 40:1992;272-281.
27. Placeway, P., Chen, S., Eskenazi, M., Jain, U., Parikh, V., Raj, B., Ravishankar, M., Rosenfeld, R., Seymore, K., Siegler, M., Stern, R., Thayer, E., 1997. The 1996 Hub-4 Sphinx-3 System. In: Proc. DARPA Speech Recognition Workshop, February 1997, pp. 95-100.
28. Rahim, M., Lee, C.H., Juang, B.H., 1997. Discriminative utterance verification for correct digits recognition. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., May 1997, Vol. 5, pp. 266-277.
29. San-Segundo, R., Pellom, B., Hacioglu, K., Ward, W., Pardo, J.M., 2001. Confidence measures for dialogue systems. Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., Salt Lake City, May 2001, Vol. 1, pp. 492-495.
30. Schaaf, T., Kemp, T., 1997. Estimating confidence using word lattices. Proc. EuroSpeech 1997, Rhodes, Greece pp. 827-830.
31. Steinbiss, V., Tran, B.-H., Ney, H., 1994. Improvements in beam search. Proc. 1994 Internat. Conf. on Spoken Language Process., ICSLP'94, Yokohama, Japan, Vol. 1, pp. 397-400.
32. Sukkar, R.A., 1994. Rejection for connected digit recognition based on GPD segmental discrimination. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., Adelaide, 1994, Vol. I, pp. 381-284.
33. Sukkar R.A., Lee C.-H. Vocabulary independent discriminative utterance verification for non-keyword rejection in sub-word based speech recognition. IEEE Trans. Speech Audio Process. 4(6):1996;420-429.
34. Sukkar, R.A., Setlur, A.R., Rahim, M.G., Lee, C.-H., 1996b. Utterance verification of keyword strings using word-based minimum verification error (WB-MVE) training. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., 1996, pp. 518-521.
35. Thomas D.E., Adams J., Schmit H. A model and methodology for hardware-software codesign. IEEE Design Test Comput. 10(3):1993;6-15.
36. Vergyri, D., 2000. Use of word level side information to improve speech recognition. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., 2000, pp. 1782-1785.
37. Weintraub, M., Beaufays, F., Rivlin, Z., Konig, Y., Stolcke, A., 1997. Neural-network based measures of confidence for word recognition. In: Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process., pp. 887-890.
38. Wessel F., Schluter R., Macherey K., Ney H. Confidence measures for large vocabulary continuous speech recognition. Proc. IEEE Internat. Conf. on Acoust., Speech Signal Process. 9(3):2001;288-298.
39. Williams, G., Renals, S., 1997. Confidence measures for hybrid HMM/ANN speech recognition. In: Proc. Eurospeech 1997, Rhodes, Greece, pp. 1955-1958.
40. Wilpon J.G., Rabiner L.R., Lee C.-H., Goldman E.R. Automatic recognition of keywords in unconstrained speech using hidden Markov models. IEEE Trans. on Acoust., Speech, Signal Process. 38(11):1990;1870-1878.
41. Zhan, P., Ries, K., Gavalda, M., Gates, D., Lavie, A., Waibel, A., 1996. Janus-II: towards spontaneous Spanish speech recognition. In: Proc. 1996 Internat. Conf. on Spoken Language Process., ICSLP'96, pp. 836-839.