Stochastic trajectory modeling and sentence searching for continuous speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 5, Issue 1, 1997, Pages 33-44

  Gong, Yifan ^a,b  

^a INRIA   (France)

^b TEXAS INSTRUMENTS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY DENSITY FUNCTION; SPEECH ANALYSIS; VECTORS;

HIDDEN MARKOV MODELS (HMM); SENTENCE SEARCHING; STOCHASTIC TRAJECTORY MODELING; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 0030784572     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.554267     Document Type: Article

References (42)

1. L. R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE, vol. 77, no. 2, pp. 257-285, Feb. 1989.
2. L. E. Baum, An inequality and associated maximation technique in statistical estimation for probabilistic functions of Markov processes O. Shisha, Ed., Inequalities-Ill. New York: Academic, pp. 1-8.
3. S. Krishnan and P. V. S. Rao, Segmental phoneme recognition using piecewise linear regression Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, vol. 1, Adelaide, Australia, Apr. 1994, pp. 49-52.
4. S. Furui, Speaker-independent isolated word recognition using dynamic features of speech spectrum, IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-34, no. 1, pp. 53-59, 1986.
5. K. F. Lee, Large vocabulary speaker-independent continuous speech recognition: The SPHINX system, Ph.D. dissertation, Carnegie-Mellon Univ., Pittsburgh, PA, 1988.
6. P. F. Brown, The acoustic modeling problem in automatic speech recognition, Ph.D. dissertation, School Comput. Sei., Carnegie-Mellon Univ., Pittsburgh, PA, 1987.
7. C. J. Wellekens, Explicit time correlation in hidden Markov models for speech recognition Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Dallas, TX, 1987, pp. 384-387.
8. K. K. Paliwal, Use of temporal correlation between successive frames in a hidden Markov model based speech recognizer Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1993, vol. 2, pp. 215-218.
9. S. Takahashi, T. Matsuoka, Y. Minami, and K. Shikano. Phoneme HMMS constrained by frame correlations Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, vol. 2, 1993, pp. 219-222.
10. T. Robinson, A real-time recurrent error propagation network word recognition system Int. Conf. Acoust., Speech, Signal Processing, vol. 1, 1992, pp. 617-620.
11. L. Deng, P. Kenny, M. Lenning, and P. Mermelstein, Modeling acoustic transitions in speech by state-interpolation hidden Markov models, IEEE Trans. Signal Processing, vol. 40, no. 2, pp. 265-271, Feb. 1992.
12. B. H. Juang and L. R. Rabiner, Mixture autoregressive hidden Markov models, IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-33, no. 6, pp. 1404-1413, 1985.
13. M. Ostendorf and S. Roucos, A stochastic segment model for phonemebased continuous speech recognition, IEEE Trans. Acoust, Speech, Signal Processing, vol. 37, no. 12, pp. 1857-1869, Dec. 1989.
14. S. Roucos and M. O. Dunham, A stochastic segment model for phoneme-based continuous speech recognition Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Dallas, TX, 1987, pp. 73-76.
15. V. V. Digalakis, M. Ostendorf, and J.R. Rohlicek, Fast algorithms for phone classification and recognition using segment-based models, IEEE Trans. Signal Processing, vol.49, no. 12, pp. 2885-2896, Dec. 1992.
16. V. V. Digalakis, J. R. Rohlicek, and M. Ostendorf, ML estimation of a stochastic linear system with EM algorithm and its application to speech recognition, IEEE Trans. Speech Audio Processing, vol. 1, no. 4, pp. 431-442, Oct. 1993.
17. L. Deng, A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal, Signal Processing, vol. 27, no. 1, pp. 65-78, 1992.
18. L. Deng, M. Asmanovic, D. Sun, and J. Wu, Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states, IEEE Trans. Speech Audio Processing, vol. 2, no. 4, pp. 507-520, 1994.
19. X. D. Sun, L. Deng, and C. F. J. Wu, State-dependent time warping in the trended hidden Markov model, Signal Processing, vol. 39, no. 3, pp. 263-275, 1994.
20. O. Ghitza and M. M. Sondhi, Hidden Markov models with templates as nonstationary states: An application to speech recognition, Comput., Speech, Language, vol. 2, pp. 101-119, Apr. 1993.
21. Y. Gong and J.-P. Haton, Phoneme-based continuous speech recognition without presegmentation Proc. Europ. Conf. Speech Technol, vol. 1, pp. Edinburgh, Scotland, Sept. 1987, pp. 121-124.
22. _, Signal-to-string conversion based on high likelihood regions using embedded dynamic programming, IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 3, pp. 297-302, Mar. 1991.
23. Y. Gong, J.-P. Haton, and F. Mouria, Continuous speech recognition based on high plausibility regions Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, vol. 1, Toronto, Canada, May 1991, pp. 725-728.
24. Y. Gong and J.-P. Haton, VINICS: A continuous speech recognizer based on a new robust formulation Proc. Europ. Conf. Speech Commun. Technol., vol. III, Genova, Italy, Sept. 1991, pp. 1221-1224.
25. _, Stochastic trajectory modeling for speech recognition Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, vol. I, Adelaide, Australia, Apr. 1994, pp. 57-60.
26. Y. Gong, J.-P. Haton, and J.-F. Mari, Issues in acoustic modeling of speech for automatic speech recognition H. Niemann, R. De Mon, and G. Hanrieder, Eds, Progress and Prospects of Speech Research and Technology. INFIX: Sankt Augustin, Sept. 1994.
27. A. Papoulis. Probability, Random Variables, and Stochastic Processes, 3rd ed. New York: McGraw-Hill, 1991.
28. W. D. Goldenthal and J. R. Glass, Statistical trajectory models for phonetic recognition Proc. Int. Conf. Spoken Language Processing '94, Yokohama, Japan, Sept. 1994, pp. 1871-1873.
29. M. Afify, Y. Gong, and J.-P. Haton, Non-linear time alignment in stochastic trajectory models for speech recognition Proc. Int. Conf. Spoken Language Processing '94, vol. 1, Yokohama, Japan, Sept. 1994, pp. 291-293.
30. H. W. Sorenson and D. L. Alspach, Recursive Bayesian estimation using Gaussian sums, Automatica, vol. 7, pp. 465-497, 1971.
31. A. Ljolje and S. E. Levinson, Development of an acoustic-phonetic hidden Markov model for continuous speech recognition, IEEE Trans. Signal Processing, vol. 39, no. 1, pp. 29-39, Jan. 1991.
32. J. M. Mendel, Lessons in Digital Estimation Tlieoty. Englewood Cliffs, NJ: Prentice-Hall, 1987.
33. Y. Linde, A. Buzo, and R. M. Gray, An algorithm for the vector quantizer design, IEEE Trans. Commun., vol. COM-28, no. 1, pp. 84-95, Jan 1980.
34. G. M. White, Dynamic programming, the Viterbi algorithm, and low cost speech recognition Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing, 1978, pp. 413-417.
35. Y. Gong and J.-P. Haton, DTW-based phonetic labeling using explicit phoneme duration constraints Proc. Int. Conf. Spoken Language Processing '92, vol. II, Banff, Canada, Oct. 1992, pp. 863-866.
36. _, Iterative transformation and alignment for speech labeling Proc. Europ. Conf. Speech Commun. Technol., vol. 3, Berlin, Germany, Sept. 1993, pp. 1759-1762.
37. S. J. Young, HTK: Hidden Markov model toolkit V1.4 reference manual, Tech. Rep., Speech Group, Cambridge Univ. Eng. Dept., Cambridge, England, Sept. 1992.
38. H. Ney, Modeling and search in continuous speech recognition Proc. Etirop. Conf. Speech Technol, vol. 1, Berlin, Germany, 1993, pp. 491-498.
39. J. D. Ferguson, Variable duration models for speech Proc. Symp. Applic. Hidden Markov Models Text Speech, Princeton, NJ, 1980, pp. 143-179.
40. M. J. Russell and R. K. Moore, Explicit modeling of state occupancy in hidden Markov models for automatic speech recognition Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1985, pp. 5-8.
41. S. E. Levinson, Continuously variable duration hidden Markov models for automatic speech recognition, Comput., Speech Language, vol. 1, no. 1, pp. 29-45, 1986.
42. L. R. Rabiner, Mathematical Foundations of Hidden Markov Models, vol. F-46 of NATO ASl: Recent Advances in Speech Understanding and Dialog Systems. New York: Springer-Verlag, 1988, pp. 183-205.