A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features

Journal of the Acoustical Society of America

Volumn 95, Issue 5, 1994, Pages 2702-2719

  Deng, Li ^a   Sun, Don X ^b  

^a UNIVERSITY OF WATERLOO   (Canada)

^b STONY BROOK UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; AUTOMATION; DATA BASE; MATHEMATICAL ANALYSIS; PRIORITY JOURNAL; SPEECH DISCRIMINATION; WORD RECOGNITION;

EID: 0028234947     PISSN: 00014966     EISSN: NA     Source Type: Journal    
DOI: 10.1121/1.409839     Document Type: Article

References (39)

1. Bakis, R. (1991). “Coarticulation modeling with continuous-state HMMs,” Proceedings of the 1991 IEEE Workshop on Automatic Speech Recognition (Arden House, Harriman, New York), pp. 20–21.
2. Baum, L. E. (1972). “An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes,” Inequalities 3, 1–8.
3. Browman, C., and Goldstein, L. (1992). “Articulatory phonology: An overview,” Phonetica 49, 155–180.
4. Browman, C., and Goldstein, L. (1990). “Gestural specification using dynamically-defined articulatory structures,” J. Phon. 18, 299–320.
5. Browman, C., and Goldstein, L. (1986). “Towards an articulatory phonology,” Phonol. Yearbook 3, 219–252.
6. Chomsky, N., and Halle, M. (1968). The Sound Pattern of English (Harper and Row, New York).
7. Clements, G. N. (1985). “The geometry of phonological features,” Pho-nol. Yearbook 2, 225–252.
8. Davis, S., and Mermelstein, P. (1980). “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust. Speech Signal Process. 28 (4), 357–365.
9. Deng, L. (1993). “A stochastic model of speech incorporating hierarchical nonstationarity,” IEEE Trans. Speech Audio Process. 1 (4), 471–474.
10. Deng, L. (1992). “A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal,” Signal Process. 27 (1), 65–78.
11. Deng, L. (1991). “The semi-relaxed algorithm for parameter estimation of hidden Markov models,” Comput. Speech Language 5 (3), 231–236.
12. Deng, L., and Erler, K. (1992). “Structural design of a hidden Markov model based speech recognizer using multivalued phonetic features: Comparison with segmental speech units,” J. Acoust. Soc. Am. 92, 3058–3067.
13. Deng, L., Kenny, P. Lennig, M., Gupta, V., Seitz, F., and Mermelstein, P. (1991). “Phonemic hidden Markov models with continuous mixture output densities for large vocabulary word recognition,” IEEE Trans. Acoust. Speech, Signal Process. 39 (7), 1677–1681.
14. Deng, L., Kenny, P., Lennig, M., and Mermelstein, P. (1992). “Modeling acoustic transitions in speech by state-interpolation hidden Markov models,” IEEE Trans. Signal Process. 40 (2), 265–272.
15. Deng, L., Lennig, M., and Mermelstein, P. (1989). “Use of vowel duration information in a large vocabulary word recognizer,” J. Acoust. Soc. Am. 86, 540–548.
16. Deng, L., Lennig, M., and Mermelstein, P. (1990). “Modeling microsegments of stop consonants in a hidden Markov model based word recognizer,” J. Acoust. Soc. Am. 87, 2738–2747.
17. Deng, L., Lennig, M., Seitz, F., and Mermelstein, P. (1990). “Large vocabulary word recognition using context-dependent allophonic hidden Markov models,” Comput. Speech Language 4, 345–357.
18. Erler, K., and Deng, L. (1993). “Hidden Markov model representation of quantized articulatory features for speech recognition,” Comput. Speech Language 7 (3), 101–118.
19. Halle, M., and Stevens, K. (1991). “Knowledge of language and the sounds of speech,” in Music, Language, Speech, and Brain, edited by J. Sundberg, L. Nord, and R. Carlson (MacMillan, London), pp. 1–19.
20. Hwang, M., Huang, X., and Alieva, F. (1993). “Predicting unseen triphones with senones,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1, pp. 311–315.
21. Kenny, P., Zhao, R., Gupta, V., Lennig, M., and O’Shaughnessy, D. (1991). “Articulatory Markov models,” Proceedings of the 1991 IEEE Workshop on Automatic Speech Recognition (Arden House, Harriman, New York), pp. 22–23.
22. Lee, K., and Hon, H. (1990). “Context-dependent phonetic hidden Markov models for continuous speech recognition,” IEEE Trans. Signal Process. 38 (4), 599–609.
23. Lee, K., and Hon, H. (1989). “Speaker-independent phone recognition using hidden Markov models,” IEEE Trans. Signal Process. 37 (11), 1641–1648.
24. Lehiste, I. (1967). Readings in Acoustic Phonetics (MIT, Cambridge, MA).
25. Leung, H., Chigier, B., and Glass, J. (1993). “A comparative study of signal representations and classification techniques for speech recognition,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1, pp. 680–683.
26. McCarthy, J. (1988). “Feature geometry and dependency: a review,” Phonetica 43, 84–108.
27. Mermelstein, P. (1973). “Articulatory model for the study of speech production,” J. Acoust. Soc. Am. 53, 1070–1082.
28. Phillips, M., Glass, J., and, Zue, V. (1992). “Automatic discovery of acoustic measurements for phonetic classification,” Proceedings of the IEEE International Conference on Spoken Language Processing, Vol. 1, pp. 795–798.
29. Rabiner, L. (1989). “A tutorial on hidden Markov models and selected applications in speech recognition,” Proc. IEEE 77, 257–285.
30. Saltzman, E. (1986). “Task dynamic coordination of the speech articulators: A preliminary model,” in Generation and Modulation of Action Patterns, edited by H. Heuer and C. Fromm (Springer-Verlag, New York), pp. 129–144.
31. Saltzman, E., and Munhall, K. (1989). “A dynamical approach to gestural patterning in speech production,” Ecol. Psychol. 1 (4), 333–382.
32. Schwartz, R., Chow, Y., Roucos, S., Krasner, M., and Makhoul, J. (1984). “Improved hidden Markov modeling of phonemes for continuous speech recognition,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 35.6.1-35.6.4.
33. Stevens, K. (1986). “Models of phonetic recognition II: An approach to feature-based recognition,” in Symposium on Units and Their Representation in Speech Recognition, edited by P. Mermelstein (12th Int’l Congress on Acoustics, Montreal), pp. 67–69.
34. Stevens, K. (1989). “On the quantal nature of speech,” J. Phon. 17, 3–45.
35. Stevens, K., Manuel, S., Shattuck-Hufnagel, S., and Liu, S. (1992). “Implementation of a model for lexical access based on features,” Proc. Int. Conf. Spoken Language Process. 1, 499–502.
36. Zue, V. (1985). “The use of speech knowledge in automatic speech recognition,” Proc. IEEE 73, 1602–1550.
37. Zue, V. (1991). “Notes on Speech Spectrogram Reading”, course notes, M.I.T., Cambridge, MA.
38. Zue, V., Glass, J., Goodine, D., Phillips, M., and Seneff, S. (1990). “The SUMMIT speech recognition system: Phonological modeling and lexical access,” Proc. IEEE Int. Conf. Acoust. Speech, Signal Process. 1, 49–52.
39. Zue, V., and Sia, E. (1982). “Nasal articulation in homorganic clusters in American English,” Working Papers in MIT Speech Commun. Group 1, pp. 9–17.