Abstract
In this paper, we discuss the issue of speech recognizer training from a broad perspective with root in the classical Bayes decision theory. We differentiate the method of classifier design via distribution estimation and the method of discriminative training based on the fact that in many realistic applications, such as speech recognition, the real signal distribution form is rarely known precisely. We argue that traditional methods relying on distribution estimation are suboptimal when the assumed distribution form is not the true one, and that “optimality” in distribution estimation does not automatically translate into “optimality” in classifier design. We compare the two different methods in the context of hidden Markov modeling for speech recognition. We show the superiority of the discriminative method over the distribution estimation method by citing the results of several key speech recognition experiments. In general, the discriminative method provides a 30-50% reduction in recognition errors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
L. R. Rabiner, “A tutorial on hidden Markov models and selected applications in speech recognition;” Proc. IEEE, 77(2): 257–286, February 1989
L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition, Prentice Hall, Englewood Cliffs, NJ, 1993
R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, New York: Wiley, 1973
F. Jelinek, “The development of an experimental discrete dictation recognizer,” Proc. IEEE, 73: 1616–1624, November 1985
B. H. Juang, L. R. Rabiner and J. G. Wilpon, “On the use of bandpass liftering in speech recognition,” IEEE Trans. Acoust. Speech Signal Processing, ASSP-35(7): 947–954, July 1987
B. H. Juang and L. R. Rabiner, “Hidden Markov models for speech recognition,” Technometrics. Vol. 33, No. 3, pp. 251–272, August 1991
L. E. Baum, T. Petrie, G. Soulcs and N. Weiss, “A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains,” Ann. Math. Stat.,41(1): 164–171, 1970
B. H. Juang and S. Katagiri, “Discriminative learning for minimum error classification,” IEEE Trans. Signal Processing, SP-40, No. 12, pp. 3043–3054, December 1992
Wu Chou, C. H. Lee and B. H. Juang, “Minimum error rate training based on N-best string models,” IEEE ICASSP-93 Proceedings, 11–652-655, April 1993
Wu Chou, C. H. Lee and B. H. Juang, “Segmental GPD training of a hidden Markov model based speech recognizer,” IEEE Proc. ICASSP-92, pp. 473–476, 1992
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Juang, B.H., Chou, W., Lee, C.H. (1995). Statistical and Discriminative Methods for Speech Recognition. In: Ayuso, A.J.R., Soler, J.M.L. (eds) Speech Recognition and Coding. NATO ASI Series, vol 147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-57745-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive