A study on the use of bi-directional contextual dependence in Markov random field-based acoustic modelling for speech recognition

Computer Speech and Language

Volumn 10, Issue 2, 1996, Pages 95-105

  Huo, Qiang ^a,b   Chan, Chorkin ^b  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTICS; ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PARALLEL PROCESSING SYSTEMS; VECTOR QUANTIZATION;

BI-DIRECTIONAL CONTEXTUAL DEPENDENCE; ITERATED CONDITIONAL MODES; MARKOV RANDOM FIELD;

SPEECH RECOGNITION;

EID: 0030121298     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1996.0006     Document Type: Article

References (28)

1. Abend, K., Harley, T. J. & Kanal, L. N. (1965). Classification of binary random patterns. IEEE Transactions on Information Theory 11, 538-544.
2. Besag, J. (1974). Spatial interactions and the statistical analysis of lattice systems. Journal of the Royal Statistical Society B 36, 192-236.
3. Besag, J. (1986). On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society B 48, 259-302.
4. Chellappa, R. & Jain, A. (1993). Markov Random Fields: Theory and Application. Academic Press, London.
5. Cole, R., Muthusamy, Y. & Fanty, M. (1990). The ISOLET spoken letter database. Technical Report No. CSE 90-004, Department of Computer Science and Engineering, Oregon Graduate Institute of Science and Technology.
6. Cox, T. (1977). An example of phase transition in countable one-dimensional Markov random fields. Journal of Applied Probability 14, 205-211.
7. Derin, H. & Kelly, P. A. (1989). Discrete-index Markov-type random process. Proceedings of the IEEE 77, 1485-1510.
8. Dubes, R. C. & Jain, A. K. (1989). Random field models in image analysis. Journal of Applied Statistics 16, 131-164.
9. Everitt, B. S. & Hand, D. J. (1981). Finite Mixture Distributions. London, Chapman and Hall.
10. Geman, S. & Geman, D. (1984). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence 6, 721-741.
11. Huo, Q. & Chan, C. (1994). Contextual vector quantization for speech recognition with discrete hidden Markov model. Proceedings of 1994 International Symposium on Speech, Image Processing & Neural Networks, Hong Kong, pp. 698-701. Also in Pattern Recognition 28, 513-517, 1995.
12. Huo, Q. & Chan, C. (1994). Contextual vector quantization for speech recognition with discrete hidden Markov model. Proceedings of 1994 International Symposium on Speech, Image Processing & Neural Networks, Hong Kong, pp. 698-701. Also in Pattern Recognition 28, 513-517, 1995.
13. Jelinek, F. & Mercer, R. L. (1980). Interpolated estimation of Markov source parameters for sparse data. In Pattern Recognition in Practice (E. S. Gelsema and L. N. Kanal, eds), pp. 381-397. Amsterdam, North-Holland.
14. Juang, B.-H. & Rabiner, L. R. (1991). Issues in using hidden Markov models for speech recognition. In Advances in Speech Signal Processing (S. Furui and M. M. Sondhi, eds), pp. 509-553. New York: Marcel Dekker.
15. Kriouile, A., Mari, J.-F. & Hanton, J.-P. (1990). Some improvements in speech recognition algorithms based on HMM. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Albuquerque, NM, pp. 545-548.
16. Lee, C.-H., Rabiner, L. R., Pieraccini, R. & Wilpon, J. G. (1990). Acoustic modeling for large vocabulary speech recognition. Computer Speech and Language 4, 127-165.
17. Leung, S.-L., Chee, P.-C., Chan, C. & Huo, Q. (1995). Contextual vector quantization modelling of hand-printed Chinese character recognition. Proceedings of the IEEE International Conference on Image Processing, Washington, DC, pp. 432-435.
18. Linde, Y., Buzo, A. & Gray, R. M. (1980). An algorithm for vector quantizer design. IEEE Transactions on Communication 28, 84-95.
19. Lucke, H. (1995). Improved acoustic modelling for speech recognition using 2D Markov random fields. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Detroit, MI, pp. 540-543.
20. McLachlan, G. J. & Basford, K. E. (1988). Mixture Models: Inference and Applications to Clustering. New York: Marcel Dekker.
21. Moussouris, J. (1974). Gibbs and Markov random systems with contraints. Journal of Statistical Physics 10, 11-31.
22. Noda, H. & Shirazi, M. N. (1994). An MRF-based parallel processing algorithm for speech recognition using linear predictive HMM. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, Australia, pp. I-597-600.
23. Rabiner, L. R. & Juang, B.-H. (1993). Fundamentals of Speech Recognition. Englewood Cliffs, NJ, Prentice-Hall.
24. Redner, R. A. & Walker, H. F. (1984). Mixture densities, maximum likelihood and the EM algorithm. SIAM Review 26, 195-239.
25. Stone, M. (1961). The opinion pool. The Annals of Mathematical Statistics 32, 1339-1342.
26. Titterington, D. M., Smith, A. F. M. & Makov, U. E. (1985). Statistical Analysis of Finite Mixture Distributions. London: Wiley.
27. Watson, B. & Tsoi, A. C. (1992). Second order hidden Markov models for speech recognition. Proceedings of the Australian Speech Science and Technology Conference, Brisbane, Australia, pp. 146-151.
28. Zhao, Y.-X., Atlas, L. E. & Zhuang, X.-H. (1991). Applications of the Gibbs distribution to hidden Markov modelling in speaker independent isolated word recognition. IEEE Transactions on Signal Processing 39, 1291-1299.