Speech recognition using autosegmental representation of phonological units with interface to the trended HMM

Speech Communication

Volumn 23, Issue 3, 1997, Pages 211-222

  Deng, Li ^a  

^a UNIVERSITY OF WATERLOO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATA THEORY; DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PATTERN RECOGNITION SYSTEMS; SPEECH ANALYSIS;

AUTOSEGMENTAL PHONOLOGY; HIDDEN MARKOV MODELS (HMM);

SPEECH RECOGNITION;

EID: 0031273517     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(97)00047-2     Document Type: Article

References (32)

1. Bakis, R., 1991. Coarticulation modeling with continuous-state HMMs. In: Proc. IEEE Workshop Automatic Speech Recognition. Harriman, New York, pp. 20-21.
2. Bakis, R., 1993. An articulatory-like speech production model with controlled use of prior knowledge, notes from Frontiers in Speech Processing, CD-ROM.
3. Bitar, N., Espy-Wilson, C., 1995. Speech parameterization based on phonetic features: Application to speech recognition. In: Proc. Eurospeech, Vol. 2, pp. 1411-1414.
4. Blackburn, C., Young, S., 1995. Towards improved speech recognition using a speech production model. In: Proc. Eurospeech, Vol. 2, pp. 1623-1626.
5. Browman, C., Goldstein, L., 1992. Articulatory phonology: An overview. Phonetica 49, 155-180.
6. Deng, L., 1992. A generalized hidden Markov model with stateconditioned trend functions of time for the speech signal. Signal Processing 27 (1), 65-78.
7. Deng, L., Braam, D., 1994. Context-dependent Markov model structured by locus equations: Application to phonetic classification. J. Acoust. Soc. Amer. 96, 2008-2025.
8. Deng, L., Erler, K., 1990. Structural design of an HMM speech recognizer using multi-valued phonetic features: Comparison with segmental speech units. J. Acoust. Soc. Amer. 92, 3058-3067.
9. Deng, L., Sameti, H., 1996. Transitional speech units and their representation by the regressive Markov states: Applications to speech recognition. IEEE Trans. Speech Audio Process. 4 (4), 301-306.
10. Deng, L., Sun, D., 1994. A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features. J. Acoust. Soc. Amer. 95, 2702-2719.
11. Deng, L., Lennig, M., Mermelstein, P., 1990. Modeling microsegments of stop consonants in a hidden Markov model based word recognizer. J. Acoust. Soc. Amer. 87, 2738-2747.
12. Deng, L., Aksmanovic, M., Sun, D., Wu, J., 1994. Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states. IEEE Trans. Speech Audio Process. 2 (4), 507-520.
13. Deng, L., Wu, J., Sameti, H., 1995. Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 385-388.
14. Eide, E., 1993. A linguistic feature representation of the speech waveform. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 2, pp. 483-486.
15. Goldsmith, J.A., 1990. Autosegmental and Metrical Phonology. Blackwell, Oxford.
16. Hwang, M., Huang, X., Alleva, F., 1993. Predicting unseen triphones with senones. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 311-315.
17. Huckvale, M., 1994. Tiered segmentation of speech: Opportunities, methods, problems and challenges. In: Speech, Hearing, and Language, Vol. 7. University College London, pp. 133-152.
18. Juang, B.H., Rabiner, L.R., 1990. The segmental k-means algorithm for estimating parameters of hidden Markov models. IEEE Trans. Speech Audio Process. 38, 1639-1641.
19. Kenny, P., et al., 1991. Articulatory Markov models. In: Proc. IEEE Workshop Automatic Speech Recognition. Harriman, New York, pp. 22-23.
20. Keyser, J., Stevens, K., 1994. Feature geometry and the vocal tract. Phonology 11 (2), 207-236.
21. Lass, N. (Ed.), 1995. Principles of Experimental Phonetics. Mosby, London.
22. Lee, K., Hon, H., 1989. Speaker-independent phone recognition using hidden Markov models. IEEE Trans. Signal Process. 37 (11), 1641-1648.
23. Liu, S., 1995. Landmark detection for distinctive feature-based speech recognition. Ph.D. Thesis, MIT.
24. Mahkoul, J., Schwartz, R., 1995. State of the art in continuous speech recognition. Proc. Nat. Acad. Sci. USA 92, 9956-9963.
25. Meng, H., Zue, V., 1991. Signal representation comparison for phonetic classification. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 285-288.
26. Pereira, C., Riley, M., 1996. Speech recognition by composition of weighted finite automata. CMP-LG archive paper 9603001.
27. Randolph, M., 1994. Speech analysis based on articulatory behavior. J. Acoust. Soc. Amer. 95, 1aSP15.
28. Sagey, E., 1986. The representation of features and relations in nonlinear phonology. PH.D. Dissertation, MIT, Cambridge, MA.
29. Sheikhzadeh, H., Deng, L., 1994. Waveform-based speech recognition using hidden filter models: Parameter selection and sensitivity to power normalization. IEEE Trans. Speech Audio Process. 2, 80-91.
30. Simons, A.J.H., 1988. A quantitative model of the articulators. In: Proc. 8th European Conf. on Artificial Intelligence, pp. 464-466.
31. Stevens, K., et al., 1992. Implementation of a model for lexical access based on features. In: Proc. ICSLP, Vol. 1, pp. 499-502.
32. Young, S. 1995. Large vocabulary continuous speech recognition: A review. In: Proc. IEEE Workshop on Automatic Speech Recognition, Snowbird, UT, pp. 3-28.