Bayesian triphone model

Computer Speech and Language

Volumn 13, Issue 2, 1999, Pages 195-206

  Ming, Ji ^a   Smith, F Jack ^a  

^a QUEEN'S UNIVERSITY BELFAST   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PARAMETER ESTIMATION; SPEECH ANALYSIS; SPEECH SYNTHESIS; STATISTICAL METHODS;

BAYESIAN STATISTICS; MIXTURE-GAUSSIAN HIDDEN MARKOV MODELS;

CONTINUOUS SPEECH RECOGNITION;

EID: 0033106612     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1999.0120     Document Type: Article

References (25)

1. Bellegarda, J. R. & Nahamoo, D. (1990). Tied mixture continuous parameter modelling for speech recognition. IEEE Transactions on Acoustics, Speech and Signal Processing, 38, 2033-2045.
2. Chen, R. & Jamieson, L. H. (1996). Explicit modelling of coarticulation in a statistical speech recognizer. Proceedings of International Conference on Acoustics, Speech and Signal Processing '96, Atlanta, GA, pp. 463-466.
3. Deng, L., Aksmanovic, M., Sun, D. & Wu, J. (1994). Speech recognition using hidden Markov models with polynominal regression functions as nonstationary states. IEEE Transactions on Speech and Audio Processing, 2, 507-520.
4. Deng, L. & Sameti, H. (1996). Transitional speech units and their representation by regressive Markov states: application to speech recognition. IEEE Transactions on Speech and Audio Processing, 4, 301-306.
5. Digalakis, V., Monaco, P. & Murveit, H. (1996). Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers. IEEE Transactions on Speech and Audio Processing, 4, 281-289.
6. Garofolo, J., Lamel, L., Fisher, W., Fiscus, J., Pallett, D. & Dahlgren, N. (1993). DARPA TIMIT Acoustic-phonetic continuous speech corpus CD-ROM. NISTIR 4930.
7. Huang, X. (1992). Phoneme classification using semicontinuous hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing, 40, 1062-1067.
8. Hwang, M. & Huang, X. (1993). Shared-distribution hidden Markov models for speech recognition. IEEE Transactions on Speech and Audio Processing, 1, 414-420.
9. Juang, B. H. (1985). Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains. AT & T Technical journal, 64, 1235-1249.
10. Lamel, L. & Gauvain, J. (1993). High performance speaker-independent phone recognition using CDHMM. Proceedings of EUROSPEECH'93, Berlin, Germany, pp. 121-124.
11. Lee, K. F. (1990). Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition. IEEE Transactions on Acoustics, Speech and Signal Processing, 38, 599-609.
12. Lee, C. H., Juang, B. H., Chou, W. & Molina-Perez, J. (1996). A study on task-independent subword selection and modelling for speech recognition. Proceedings of International Conference on Acoustics, Speech and Signal Processing '96, Philadelphia, PA, pp. 1820-1823.
13. Lee, K. F. & Hon, H. W. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing, 37, 1641-1648.
14. Lee, K. F., Hon, H. W. & Reddy, R. (1990) An overview of the SPHINX speech recognition system. IEEE Transactions on Acoustics, Speech and Signal Processing, 38, 35-44.
15. Ljolje, A. (1994). High accuracy phone recognition using context clustering and quasi-triphonic models. Computer Speech and Language, 8, 129-151.
16. Ming, J., O'Boyle, P., Owens, M. & Smith, F. J. (1999). A Bayesian approach for building triphone models for continuous speech recognition. To be published in IEEE Transactions on Speech and Audio Processing, 1999.
17. Ming, J. & Smith, F. J. (1996). Modeling of the inter-frame dependence in an HMM using conditional Gaussian mixtures. Computer Speech and Language, 10, 229-247.
18. Paul, D. B. (1990). The Lincoln tied-mixture HMM continuous speech recognizer. In Proceedings of DARPA Speech and Natural Language Workshop, Pacific Grove, CA, pp. 332-336.
19. Robinson, A. (1994). An application of recurrent nets to phone probability estimation. IEEE Transactions on Neural Networks, 5, 298-305.
20. Schwartz, R., Chow, Y., Kimball, O., Roucos, S., Krasner, M. & Makhoul, J. (1985). Context-dependent modeling for acoustic-phonetic recognition of continuous speech. Proceedings of International Conference on Acoustics, Speech and Signal Processing '85, Tampa, FL, pp. 1205-1208.
21. Takami, J. & Sagayama, S. (1992). A successive state splitting algorithm for efficient allophone modelling. Proceedings of International Conference on Acoustics, Speech and Signal Processing '92, San Francisco, CA, pp. 573-576.
22. Takami, J. & Sagayama, S. (1995). Four-level tied-structure for efficient representation of acoustic modelling. Proceedings of International Conference on Acoustics, Speech and Signal Processing '95, Detroit, MI, pp. 520-523.
23. Young, S. (1996). A review of large-vocabulary continuous-speech recognition. IEEE Signal Processing Magazine, 13, 45-57.
24. Young, S. & Woodland, P. (1994). State clustering in HMM-based continuous speech recognition. Computer Speech and Language, 8, 369-384.
25. Zeljkovic, I. & Narayanan, S. (1996). Improved HMM phone and triphone models for real-time ASR telephony applications. Proceedings of ICSLP '96, Philadelphia, PA, pp. 1105-1108.