BAYESIAN ADAPTIVE LEARNING OF THE PARAMETERS OF HIDDEN MARKOV MODEL FOR SPEECH RECOGNITION

被引：41
作者：
HUO, Q [1 ]
CHAN, C [1 ]
LEE, CH [1 ]
机构：
[1] UNIV HONG KONG,DEPT COMP SCI,HONG KONG,HONG KONG
来源：
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING | 1995年 / 3卷 / 05期
关键词：
D O I：
10.1109/89.466661
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
In this paper, a theoretical framework for Bayesian adaptive training of the parameters of discrete hidden Markov model (DHMM) and of semi-continuous HMM (SCHMM) with Gaussian mixture state observation densities is presented, In addition to formulating the forward-backward MAP (maximum a posteriori) and the segmental MAP algorithms for estimating the above HMM parameters, a computationally efficient segmental quasi-Bayes algorithm for estimating the state-specific mixture coefficients in SCHMM is developed, For estimating the parameters of the prior densities, a new empirical Bayes method based on the moment estimates is also proposed. The MAP algorithms and the prior parameter specification are directly applicable to training speaker adaptive HMM's, Practical issues related to the use of the proposed techniques for HMM-based speaker adaptation are studied, The proposed MAP algorithms are shown to be effective especially in the cases in which the training or adaptation data are limited.
引用
收藏
页码：334 / 345
页数：12
相关论文
共 46 条
[31]  
Linde Y., Buzo A., Gray R.M., An algorithm for vector quantizer design, IEEE Trans. Commun., COM-28, pp. 84-95, (1980)
[32]  
Liporace L.R., Maximum likelihood estimation for multivariate observations of Markov sources, IEEE Trans. Inform. Theory, IT-28, pp. 729-734, (1982)
[33]  
Makov U.E., Smith A.F.M., A quasi-Bayes unsupervised learning procedure for priors, IEEE Trans. Inform. Theory, IT-23, 6, pp. 761-764, (1977)
[34]  
Maritz J.S., Lwin T., Empirical Bayes Methods, (1989)
[35]  
Martin J.J., Bayesian Decision Problems and Markov Chains. New York: Wiley, (1967)
[36]  
Mathan L., Miclet L., Speaker hierarchical clustering for improving speaker independent HMM word recognition, Proc. ICASSP-90, pp. 149-152, (1990)
[37]  
Nakamura S., Akabane T., A neural speaker model for speaker clustering, Proc. ICASSP-91 Toronto, pp. 853-856, (1991)
[38]  
Rabiner L.R., A tutorial on hidden Markov models and selected applications in speech recognition, Proc. IEEE, 77, 2, pp. 257-286, (1989)
[39]  
Rabiner L.R., Lee C.-H., Juang B.-H., Wilpon J.-G., HMM clustering for connected word recognition, Proc. ICASSP-89, pp. 405-408, (1989)
[40]  
Rabiner L.R., Wilpon J.G., Juang B.-H., A segmental k-means training procedure for connected word recognition, ATT Tech. J., 65, 3, pp. 21-31, (1986)
12345