Abstract
We present a mathematical framework for Bayesian adaptive learning of the parameters of stochastic models. Maximum a posteriori (MAP) estimation algorithms are developed for hidden Markov models and for a number of useful models commonly used in automatic speech recognition and natural language processing. The MAP formulation offers a way to combine existing prior knowledge and a small set of newly acquired task-specific data in an optimal manner. It is therefore ideal for adaptive learning applications such as speaker and task adaptation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
A. Acero and R. Stern, “Environmental Robustness in Automatic Speech Recognition,” Proc. ICASSP-90, Albuquerque, pp.849–852, April 1990.
L. E. Baum, T. Petrie, G. Soules and N. Weiss, “A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains,” Annal Math. Stat., Vol. 41, pp. 164–171, 1970.
J. R. Bellegarda and D. Nahamoo, “Tied Mixture Continuous Parameter Modeling for Speech Recognition,” IEEE Trans. Acoust., Speech, Signal Processing, Vol. 38, No. 12, pp. 2033–2045, December 1990.
S. J. Cox and J. S. Bridle, “Unsupervised Speaker Adaptation by Probabilistic Fitting,” Proc. ICASSP-89, Glasgow, pp. 294–297, May 1989.
M. DeGroot, Optimal Statistical Decisions, McGraw-Hill, 1970.
A. Dempster, N. Laird and D. Rubin, “Maximum Likelihood from Incomplete Data via the EM algorithm,” J. Roy. Statist. Soc. Ser. B, 39, pp. 1–38, 1977.
S. Della Pietra, V Della Pietra, R. L. Mercer and S. Roukos, “Adaptive Language Modeling Using Minimum Discriminant Estimation,” Proc. ICASSP-92, San Francisco, pp. 633–636, April 1992.
R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, John Wiley & Sons, New York, 1973.
S. Furui, “Unsupervised Speaker Adaptation Method Based on Hierarchical Spectral Clustering” Proc. ICASSP-89, Glasgow, pp. 286–289, May 1989.
J.-L. Gauvain and C.-H. Lee, “Bayesian Learning for Hidden Markov Models With Gaussian Mixture State Observation Densities,” Speech Communication, Vol. 11, Nos. 2-3, pp. 205–214, 1992.
J.-L. Gauvain and C.-H. Lee, “Maximum A Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains,” to appear in IEEE Trans. Speech and Audio Processing, Vol. 2, No. 2, 1994.
I. J. Good, “The Population Frequencies of Species and the Estimation of Population Parameters,” Biometrika, Vol. 40, pp. 237–264, 1953.
H. Hattori and S. Sagayama, “Vector Field Smoothing Principle for Speaker Adaptation,” Proc. ICSLP-92, Banff, pp. 381–384, October 1992.
C. T. Hemphill, J. J. Godfrey and G. D. Doddington, “The ATIS Spoken Language System Pilot Corpus”, Proc. DARPA Speech and Natural Language Workshop, Hidden Valley, PA, 1990.
H.-W. Hon, “Vocabulary-Independent Speech Recognition: The VOCIND System,” Ph. D. Thesis, School of Computer Science, Carnegie Mellon University, March 1992.
X. Huang and M. A. Jack, “Semi-continuous hidden Markov models for speech signal,” Computer, Speech and Language, Vol. 3, No. 3, pp. 239–251, 1989.
Q. Huo, C. Chan and C.-H. Lee, “Bayesian Learning of the Parameters of Discrete and Tied Mixture HMMs for Speech Recognition,” Proc. EuroSpeech-93, Berlin, pp. 1567–1570, September 1992.
F. Jelinek and R. L. Mercer, “Interpolated Estimation of Markov Source Parameters from Sparse Data,” in Pattern Recognition in Practice, E. S. Gelsema and L. N. Kanal, Editors, North-Holland Publishing Co., Amsterdam, 1980.
F. Jelinek, “The Development of An Experimental Discrete Dictation Recognizer,” Proc. IEEE 73, pp. 1616–1624, 1985.
F. Jelinek, B. Merialdo, S. Roukos and M. Strauss, “A Dynamic Language Model For Speech Recognition,” Proc. DARPA Speech and Natural Language Workshop, Pacific Grove, pp. 293–295, 1991.
B.-H. Juang, “Maximum-Likelihood Estimation for Mixture Multivariate Stochastic Observations of Markov Chains “ AT&T Technical Journal, Vol. 64, No. 6, 1985.
S. M. Katz, “Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recognizer,” IEEE Trans. Acoust., Speech, Signal Processing, Vol. 35, No. 3, pp. 400–401, 1987.
R. Lau, R. Rosenfield and S. Roukos,“Trigger-Based Language Models: A Maximum Entropy Approach,” Proc. ICASSP-93, Minneapolis, pp. 11–45-48, 1993.
C.-H. Lee, C.-H. Lin and B.-H. Juang, “A Study on Speaker Adaptation of the Parameters of Continuous Density Hidden Markov Models” IEEE Trans, on ASSP, Vol. ASSP-39, No. 4, pp. 806–814, April 1991.
C.-H. Lee, E. Giachin, L. R. Rabiner, R. Pieraccini and A. E. Rosenberg, “Improved acoustic modeling for large vocabulary continuous speech recognition,” Computer Speech and Language, Vol. 6, No. 2, pp. 103–127, April 1992.
C.-H. Lee and J.-L. Gauvain, “Speaker Adaptation Based on MAP Estimation of HMM Parameters,” Proc. IEEE ICASSP-93, Minneapolis, pp. 11–652-655, April 1993.
K.-F. Lee, Automatic Speech Recognition-The Development of the SPHINX-System, Kluwer Academic Publishers, Boston, 1989.
L. R. Liporace, “Maximum Likelihood Estimation for Multivariate Observations of Markov Sources,” IEEE Trans. Inform. Theory, vol. IT-28, No. 5, pp. 729–734, 1982.
T. Matsuoka and C.-H. Lee, “A Study of On-line Bayesian Adaptation for HMM-Based Speech Recognition,” Proc. EuroSpeech-93, Berlin, pp. 815–818, September 1993.
N. Merhav and C.-H. Lee, “A Minimax Classification Approach with Application to Robust Speech Recognition,” IEEE Trans. Speech and Audio Processing, Vol. 1, No. 1, pp. 90–100, January 1993.
P. Placeway, R. Schwartz, P. Fung and L. Nguyen, “The Estimation of Powerful Language Models from Small and Large Corpora“ Proc. ICASSP-93, Minneapolis, Vol. 2, pp. 33–36, 1993.
P. J. Price, W. Fisher, J. Bernstein, and D. Palicu, “A Database for Continuous Speech Recognition in a 1000-Word Domain,” Proc. ICASSP-88, New York, pp. 651–654, April 1988.
L. R. Rabiner, J. G. Wilpon and B.-H. Juang, “A Segmental K-Means Training Procedure for Connected Word Recognition,” AT&T Tech. Journal, Vol. 65, pp. 21–31, 1986.
L. R. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition, Prentice Hall, 1993.
R. A. Redner and H. F. Walker, “Mixture Densities, Maximum Likelihood and the EM Algorithm,” SIAM Review, vol. 26, no. 2, pp. 195–239, April 1984.
H. Robbins, “The Empirical Bayes Approach to Statistical Decision Problems,” Ann. Math. Statist., vol. 35, pp. 1–20, 1964.
R. Schwartz and F. Kubala, “Hidden Markov Models and Speaker Adaptation,” in Speech Recognition and Understanding-Recent Advances, Trends and Applications, edited by P. Laface and R. De Mori, NATO ASI Series F75, pp. 31–57, 1991.
Y. Zhao, “A New Speaker Adaptation Technique Using Very Short Calibration Speech,” Proc. ICASSP-93, Minneapolis, pp. 11–592-595, April 1993.
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
Lee, CH., Gauvain, JL. (1995). Adaptive Learning in Acoustic and Language Modeling. 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_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive