Deterministically annealed design of hidden Markov model speech recognizers

IEEE Transactions on Speech and Audio Processing

Volumn 9, Issue 2, 2001, Pages 111-126

  Rao, Ajit V ^a,b   Rose, Kenneth ^b  

^a MICROSOFT   (United States)

^b University of California   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; SIMULATED ANNEALING;

DETERMINISTIC ANNEALING (DA) DESIGNS; GENERALIZED PROBABILISTIC DESCENT (GPD); HIDDEN MARKOV MODELS (HMM);

SPEECH RECOGNITION;

EID: 0035248922     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.902278     Document Type: Article

References (40)

1. L. R. Bahl, P. F. Brown, P. V. DeSouza, and R. L. Mercer, " Maximum mutual information estimation of hidden Markov model parameters," in Proc. Int. Conf. Acoustic, Speech, Signal Processing, vol. 1, 1986, pp. 49-52.
2. _, " A new algorithm fot the estimation of hidden Markov model parameters," in Proc. Int. Conf. Acoustic, Speech, Signal Processing, 1988, pp. 493-496.
3. J. K. Baker, " Stochastic modeling for automatic speech recognition," in Speech Recognition, D. R. Reddy, Ed. New York: Academic, 1975, pp. 521-542.
4. L. E. Baum and T. Pétrie, " Statistical inference for probabilistic functions of finite state Markov chains," Ann. Math. Statist., vol. 37, pp. 1554-1563, 1966.
5. L. E. Baum, T. Pétrie, G. Soûles, and N. Wciss, " A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains," Math. Statist., vol. 41, no. 1, pp. 164-171, 1970.
6. H. Bourlard, Y. Konig, N. Morgan, and C. Ris, " A new training algorithm for hybrid HMM/ANN speech recognition systems," in Signal Processing VIII, Theories Applications, Proc. EUS1PCO-96. 8lh Etir. Signal Processing Conf., vol. 1, pp. 101-104.
7. P.-C. Chang and B.-H. Juang. " Discriminative training of dynamic programming based speech recognizers," IEEE Trans. Speech Audio Processing, vol. 1, pp. 135-143, Apr. 1993.
8. _, " Discriminative template training for dynamic programming speech recognizers," in Proc. Int. Conf. Acoustic, Speech, Signal Processing, vol. 1, 1992, pp. 493-496.
9. W. Chou, B.-H. Juang, and C.-H. Lee, " Segmental GPD training of HMM based speech recognizer," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, 1992, pp. 473-476.
10. R. Cole, R. Stern, and M. Lasry, " Performing fine phonetic distinctions: Templates vs. Frames," in Proc. Int. Conf. Acoustic, Speech, Signal Processing, 1982, pp. 558-561.
11. R. Cole, Y. Muthuswamy, and M. Fanty, " The ISOLET spoken letter database," Oregon Graduate Institute, Tech. Rep. 90-004, 1990.
12. M. Fanty and R. Cole, " Spoken letter recognition," in Proc. Neural Information Processing Systems Conf, Nov. 1990, pp. 45-51.
13. J. D. Ferguson, " Hidden Markov analysis: An introduction," in Hidden Markov Models for Speech. Princeton, NJ: Inst. Defense Analysis, 1980.
14. A. Gersho and R. M. Gray, Vector Quantization and Signal Compression. Norwell, MA: Kluwer, 1992.
15. C. Gelin-Huet, K. Rose, and A. Rao, " The deterministic annealing approach for discriminative continuous HMM design," in Proc. Eitrospcech, vol. 7, 1999, pp. 2717-2720.
16. J.-S. R. Jang, C.-T. Sun, and E. Mizutani, Nenro-Fiizzy and Soft Computing: A Computer Approach to Learning and Machine Intelligence. Englewood Cliffs, NJ: Prentice-Hall, 1997.
17. F. Jelinek, " Continuous speech recognition by statistical methods," Proc. IEEE, vol. 64, pp. 532-556, Apr. 1972.
18. B.-H. Juang, W. Chou, and C.-H. Lee, " Minimum classification error rate methods for speech recognition," IEEE Trans. Speech Audio Processing, vol. 5, pp. 257-265, May 1997.
19. B.-H. Juang and S. Katagiri, " Discriminative learning for minimum error classification," IEEE Trans. Signal Processing, vol. 40, pp. 3043-3054, Dec. 1992.
20. J.-C. Junqua, " SmarTspelL: A multipass recognition system for name retrieval over the telephone," IEEE Trans. Speech Audio Processing, vol. 5, pp. 173-182, Mar. 1997.
21. S. Katagiri, B.-H. Juang, and C.-H. Lee, " Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method," Proc. IEEE, vol. 86, pp. 2345-2373, Nov. 1998.
22. Y. Linde, A. Buzo, and R. M. Gray, " An algorithm for vector quantizer design," IEEE Trans. Commun., vol. 28, pp. 84-95, Jan. 1980.
23. P. C. Loizou and A. S. Spanias, " High performance alphabet recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 430-445, Nov. 1996.
24. E. McDermott and S. Katagiri, " Prototype-based minimum classification error/generalized probabilistic descent training for various speech units," Comput. Speech Lang., vol. 8, pp. 351-368, Oct. 1994.
25. D. Miller, A. Rao, K. Rose, and A. Gersho, " A global optimization technique for statistical classifier design," IEEE Trans. Signal Processing, vol. 44, pp. 3108-3122, Dec. 1996.
26. D. Miller, K. Rose, and P. A. Chou, " Deterministic annealing for trellis quantizer and HMM design using Baum-Weich re-estimation," in Proc. Int. Conf. Acoustic, Speech, Signal Processing, vol. 5, 1994, pp. 261-264.
27. J. W. Picone, " Signal modeling techniques in speech recognition," Proc. IEEE, vol. 81, pp. 1215-1247, Sept. 1993.
28. W. H. Press, B. P. Flannery, S.A. Teulosky, and W. T. Vetterling, Numerical Recipes In C: The Art of Scientific Computing. Cambridge, MA: Cambridge Univ. Press, 1988.
29. L. R. Rabiner, " A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, pp. 257-285, Feb. 1989.
30. L. R. Rabiner and B.-H. Juang, " An introduction to hidden Markov models," IEEEASSP Mag., pp. 4-16, Jan. 1986.
31. _, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
32. L. R. Rabiner, S. Levinson, A. Rosenberg, and J. Wilpon, " Speaker independent recognition of isolated words using clustering techniques," IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-27, pp. 336-349, Aug. 1979.
33. L. R. Rabiner and J. Wilpon, " Some performance benchmarks for isolated word speech recognition systems," Comput. Speech Lang., vol. 2, pp. 343-357, 1987.
34. A. Rao, D. Miller, K. Rose, and A. Gersho, " A deterministic annealing approach for parsimonious design of piecewise regression models," IEEE Trans. Pattern Anal. Machine Intell, vol. 21, pp. 159-173, Feb. 1999.
35. _, " A generalized VQ method for combined compression and estimation," in Proc. Int. Conf. Acoustic, Speech, Signal Processing, 1996, pp. 2032-2035.
36. _, " Mixture of experts regression modeling by deterministic annealing," IEEE Trans. Signal Processing, vol. 45, pp. 2811-2820, Nov. 1997.
37. K. Rose, " Deterministic annealing for clustering, compression, classification, regression, and related optimization problems," Proc. IEEE, vol. 86, pp. 2210-2239, Nov. 1998.
38. K. Rose, E. Gurewitz, and O. C. Fox, " Statistical mechanics and phase transitions in clustering," Phys. Rev. Lett., vol. 65, pp. 945-948, 1990.
39. _, " Vector quantization by deterministic annealing," IEEE Trans. Inform. Theory, vol. 38, pp. 1249-1258, July 1992.
40. _, " Constrained clustering as an optimization method," IEEE Trans. Pattern Anal. Machine Inlell., vol. 15, pp. 785-794, Aug. 1993.