Robust speech recognition based on joint model and feature space optimization of hidden Markov models

IEEE Transactions on Neural Networks

Volumn 8, Issue 2, 1997, Pages 194-204

  Moon, Seokyong ^a,b   Hwang, Jenq Neng ^a,c  

^a IEEE   (South Korea)

^b SAMSUNG Electronics   (South Korea)

^c University of Washington   (United States)

Author keywords

Baum Welch inversion; Baum Welch reestimation; Hidden Markov model; Maximum likelihood; Minimax optimization; Minimum mean squared error; Mismatch compensation; Neural network inversion; Robust speech recognition

Indexed keywords

ALGORITHMS; ERROR COMPENSATION; LEARNING SYSTEMS; MATHEMATICAL MODELS; NEURAL NETWORKS; OPTIMIZATION; SIGNAL TO NOISE RATIO;

BAUM-WELCH INVERSION; BAUM-WELCH REESTIMATION; FEATURE SPACE OPTIMIZATION; HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD; MINIMAX OPTIMIZATION; MINIMUM MEAN SQUARED ERROR; MISMATCH COMPENSATION; NEURAL NETWORK INVERSION;

SPEECH RECOGNITION;

EID: 0031100269     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.557656     Document Type: Article

References (33)

1. A. Acero and R. M. Stern, "Environmental robustness in automatic speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Apr. 1990, pp. 849-852.
2. Y. Bengio, R. D. Mori, G. Flammia, and R. Kompe, "Global optimization of a neural network-hidden Markov model hybrid," IEEE Trans. Neural Networks, vol. 3, pp. 252-259, Mar. 1992.
3. S. F. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-29, pp. 113-120, Apr. 1979.
4. P. F. Brown, "Acoustic-phonetic modeling problem in automatic speech recognition," Ph.D. dissertation, Carnegie Mellon University, Pittsburgh, PA, 1987.
5. B. A. Carlson and M. A. Clements, "A projection-based likelihood measure for speech recognition in noise," IEEE Trans. Speech Audio Processing, vol. 2, pp. 97-102, Jan. 1994.
6. D. T. Davis, Z. Chen, L. Tsang, J. N. Hwang, and A. T. C. Chang, "Retrieval of snow parameters by iterative inversion of a neural network," IEEE Trans. Geosci. Remote Sensing, vol. 31, pp. 842-852, July 1993.
7. O. Ghitza, "Auditory models and human performance in tasks related to speech coding and speech recognition," IEEE Trans. Speech Audio Processing, vol. 2, Pt. II, pp. 115-132, Jan. 1994.
8. D. Hoskins, J. N. Hwang, and J. Vagners, "Iterative inversion of neural networks and its application to adaptive control," IEEE Trans. Neural Networks, vol. 3, pp. 292-301, Mar. 1992.
9. P. J. Huber, "A robust version of the probability ratio test," Ann. Math. Stat., vol. 36, no. 4, pp. 1753-1758, 1965.
10. J. N. Hwang, J. A. Vlontzos, and S. Y. Kung, "A systolic neural network architecture for hidden Markov models," IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp. 1967-1979, Dec. 1989.
11. J. N. Hwang and C. H. Chan, "Iterative constrained inversion of neural networks and its applications, in Proc. 24th Conf. Inform. Syst. Sci., Princeton, NJ, Mar. 1990, pp. 754-759.
12. J. N. Hwang, J. J. Choi, S. Oh, and R. J. Marks, II, "Query learning applied to partially trained multilayer perceptrons," IEEE Trans. Neural Networks, vol. 2, pp. 131-136, Jan. 1991.
13. J. N. Hwang and H. Li, "Interactive query learning for isolated speech recognition," in Proc. IEEE Int. Wkshp. Neural Networks Signal Processing, Helsinger, Denmark, Sept. 1992, pp. 93-102.
14. A. Isidori, Nonlinear Control Systems. New York: Springer-Verlag, 1995.
15. B. H. Juang, "Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains," AT&T Tech. J., vol. 64, no. 6, pp. 1235-1249, July 1985.
16. _, "Speech recognition in adverse environment," Comput. Speech Language, vol. 5, no. 3, pp. 275-294, 1991.
17. B. H. Juang and K. K. Paliwal, "Hidden Markov models with first-order equalization for noisy speech recognition," IEEE Trans. Signal Processing, vol. 40, pp. 2136-2143, Sept. 1992.
18. B. H. Juang and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Trans. Signal Processing, vol. 40, pp. 3043-3054, Dec. 1992.
19. S. Katagiri, C. H. Lee, and B. H. Juang, "New discriminative training algorithm based on the generalized probabilistic descent method," in Proc. IEEE Wkshp. Neural Networks Signal Processing, Piscataway, NJ, Aug. 1991, pp. 299-308.
20. J. S. Lim and A. V. Oppenheim, "All-pole modeling of degraded speech," IEEE Trans. Acoust., Speech, Signal Processing, vol. 26, no. 3, pp. 197-210, June 1978.
21. _, "Enhancement and bandwidth compression of noisy speech (Invited Paper)," Proc. IEEE, vol. 67, no. 12, pp. 1586-1604, Dec. 1979.
22. A. Linden and J. Kindermann, "Inversion of multilayer nets," in Proc. Int. Joint Conf. Neural Networks, Washington, D.C., June 1989, pp. 425-430.
23. D. Mansour and B. H. Juang, "A family of distortion measures based upon projection operation for robust speech recognition," IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp. 1659-1671, Nov. 1989.
24. N. Merhav and C. H. Lee, "A minimax classification approach with application to robust speech recognition," IEEE Trans. Speech Audio Processing, vol. 1, pp. 90-100, Jan. 1993.
25. S. Y. Moon and J. N. Hwang, "Noisy speech recognition via wavelet coefficient enhancement," in Proc. IEEE 26th Asilomar Conf. Signals, Syst., Comput., Monterey, CA, Oct. 1992, pp. 1086-1090.
26. _, "Robust noisy speech enhancement using wavelets," in Proc. 1st Asia Pacific Conf. Commun., vol. 2, Seoul, Korea, Aug. 1993.
27. _, "Coordinated training of noise removing networks," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, vol. 1, Minneapolis, MN, Apr. 1993, pp. 573-576.
28. _, "Noisy speech recognition using robust inversion of hidden Markov models," in Proc. EEE Int. Conf. Acoust., Speech, Signal Processing, Detroit, MI, May 1995, pp. 145-148.
29. L. T. Niles, "Modeling and learning in speech recognition: The relationship between stochastic pattern classifiers and neural networks," Ph.D. dissertation, Brown University, Providence, RI, May 1991.
30. L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
31. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," Parallel Distributed Processing (PDP): Exploration in the Microstructure of Cognition, vol. 1. Cambridge, MA: MIT Press, 1986, ch. 8, pp. 318-362.
32. S. Tamura and A. Waibel, "Noise reduction using connectionist models," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1988, pp. 553-556.
33. H. White, "Learning in artificial neural networks: A statistical perspective," Neural Computa., vol. 1, no. 4, pp. 425-464, winter 1989.