Bayesian Learning of Speech Duration Models

IEEE Transactions on Speech and Audio Processing

Volumn 11, Issue 6, 2003, Pages 558-567

  Chien, Jen Tzung ^a   Huang, Chih Hsien ^a  

^a NATIONAL CHENG KUNG UNIVERSITY   (Taiwan)

Author keywords

Adaptive duration model; Conjugate prior; Gamma distribution; Quasi Bayes estimate; Sequential learning; Speaking rate; Speech recognition

Indexed keywords

ACOUSTIC NOISE; ALGORITHMS; BROADCASTING; MARKOV PROCESSES; PROBABILITY; SPEECH ANALYSIS;

BAYESIAN LEARNING; GAMMA DISTRIBUTION; SEQUENTIAL LEARNING;

SPEECH RECOGNITION;

EID: 0347968278     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2003.818114     Document Type: Article

References (36)

1. M. Abromovitz and I. A. Stegun, Handbook of Mathematical Functions, New York: Dover, 1965.
2. A. Anastasakos, R. Schwartz, and H. Shu, "Duration modeling in large vocabulary speech recognition," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), pp. 628-631, 1995.
3. D. Burshtein, "Robust parametric modeling of durations in hidden Markov models," IEEE Trans. Speech Audio Processing, vol. 4, pp. 240-242, May 1996.
4. J.-T. Chien, "Online hierarchical transformation of hidden Markov models for speech recognition," IEEE Trans. Speech Audio Processing, vol. 7, no. 6, pp. 656-667, 1999.
5. J.-T. Chien and G.-H. Liao, "Transformation-based Bayesian predictive classification using online prior evolution," IEEE Trans. Speech Audio Processing, vol. 9, no. 4, pp. 399-410, 2001.
6. M. H. DeGroot, Optimal Statistical Decisions. New York: McGraw-Hill, 1970.
7. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc. B, vol. 39, pp. 1-38, 1977.
8. R. Dong and J. Zhu, "One use of duration modeling for continuous digits speech recognition," in Proc. Int. Con. Spoken Language Processing (ICSLP), 2002, pp. 385-388.
9. T. Fabian, T. Pfau, and G. Ruske, "Analysis of N-best output hypotheses for fast speech in large vocabulary continuous speech recognition," in Proc. EUROSPEECH, vol. 4, 2001, pp. 2535-2538.
10. R. Faltlhauser, G. Ruske, and M. Thomae, "Toward the question: Why has speaking rate such an impact on speech recognition performance," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 2002, pp. 2429-2432.
11. J. D. Ferguson, "Variable duration models for speech," in Proc. Symp. Application of Hidden Markov Models to Text and Speech, 1980, pp. 143-179.
12. J. L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Processing, vol. 2, pp. 291-298, 1994.
13. H. Gu, C. Tseng, and L. Lee, "Isolated-utterance speech recognition using hidden Markov models with bounded state durations," IEEE Trans. Signal Processing, vol. 39, pp. 1743-1752, Aug. 1991.
14. W.-W. Hung and H.-C. Wang, "HMM retraining based on state duration alignment for noisy speech recognition," in Proc. EUROSPEECH, vol. 3, 1997, pp. 1519-1522.
15. Q. Huo and C.-H. Lee, "On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate, " IEEE Trans. Speech Audio Processing, vol. 5, pp. 161-172, Mar. 1997.
16. P. Jeanrenaud, E. Eide, U. Chaudhari, J. McDonough, K. Ng, M. Siu, and H. Gish, "Reducing word error rate on conversational speech from the switchboard corpus," IEEE Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), pp. 53-56, 1995.
17. H. Kuwabara, "Acoustic and perceptual properties of phonemes in continuous speech as a function of speaking rate," in Proc. EUROSPEECH, 1997, pp. 1003-1006.
18. W.-H. Lai and S.-H. Chen, "Analysis of syllable duration models for Mandarin speech," in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), vol. 1, 2002, pp. 497-500.
19. S. E. Levinson, "Continuously variable duration hidden Markov models for automatic speech recognition," Comput. Speech Lang., vol. 1, pp. 29-45, 1986.
20. N. Mirghafori, E. Fosler, and N. Morgan, "Toward robustness to fast speech in ASR," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), pp. 335-338, 1996.
21. N. Morgan, E. Fosler, and N. Mirghafori, "Speech recognition using on-line estimation of speaking rate," in Proc. EUROSPEECH, 1997, pp. 2079-2082.
22. K. Power, "Duration modeling for improved connected digit recognition," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 1996, pp. 885-888.
23. L. R. Rabiner and B.-H Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
24. L. R. Rabiner, B.-H. Juang, S. E. Levinson, and M. M. Sondhi, "Recognition of isolated digits using hidden Markov models with continuous mixture densities," AT&T Tech. J., vol. 64, no. 6, pp. 1211-1234, 1985.
25. M. Richardson, M. Hwang, A. Acero, and X. D. Huang, "Improvement on speech recognition for fast talkers," in Proc. EUROSPEECH, vol. 1, 1999, pp. 411-414.
26. M. J. Russell and R. K. Moore, "Explicit modeling of state occupancy in hidden Markov models for automatic speech recognition," Proc. IEEE Int. Conf. Acoustic, Speech, Signal Processing (ICASSP), pp. 5-8, 1985.
27. L. Saul and M. Rahim, "Modeling the rate of speech by Markov processes on curves," in Proc. EUROSPEECH, vol. 1, 1999, pp. 415-418.
28. M. A. Siegler and R. M. Stern, "On the effects of speech rate in large vocabulary speech recognition systems," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), pp. 612-615, 1995.
29. N. Suaudeau and R. Andre-Obrecht, "An efficient combination of acoustic and supra-segmental informations in a speech recognition system," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), vol. 1, pp. 65-68, 1994.
30. Q. Summerfield, "On articulatory rate and perceptual constancy in phonetic perception," J. Exper. Psychol. Hum. Perform., vol. 7, pp. 1074-1095, 1981.
31. A. Tuerk and S. Young, "Modeling speaking rate using a between frame distance metric," in Proc. EUROSPEECH, vol. 1, 1999, pp. 419-422.
32. J. P. Verhasselt and J.-P. Martens, "A fast and reliable rate of speech detector," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 1996, pp. 2258-2261.
33. X. Wang, L. C. W. Pols, and L. F. M. ten Bosch, "Analysis of context-dependent segmental duration for automatic speech recognition," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 1996, pp. 1181-1184.
34. N. Ward and S. Nakagawa, "Automatic user-adaptive speaking rate selection for information delivery," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 2002, pp. 549-552.
35. N. B. Yoma, F. R. McInnes, M. A. Jack, S. D. Stump, and L. L. Ling, "On including temporal constraints in Viterbi alignment for speech recognition in noise," IEEE Trans. Speech Audio Processing, vol. 9, pp. 179-182, Feb. 2001.
36. N. B. Yoma and J. S. Sanchez, "MAP speaker adaptation of state duration distributions for speech recognition," IEEE Trans. Speech Audio Processing, vol. 10, pp. 443-450, Oct. 2002.