Multilayer perceptrons for state-dependent weightings of HMM likelihoods

被引:7
作者
Chung, YJ [1 ]
Un, CK [1 ]
机构
[1] KOREA ADV INST SCI & TECHNOL, DEPT ELECT ENGN, COMMUN RES LAB, YUSUNG KU, TAEJON 305701, SOUTH KOREA
关键词
speech recognition; multilayer perceptron; weighting of hidden Markov models;
D O I
10.1016/0167-6393(95)00038-0
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
This paper proposes multi-layer perceptrons (MLPs) use in state-dependent weightings of Hidden Markov Model (HMM) likelihoods. The static pattern classification ability of MLPs and the temporal processing capability of HMMs are employed in order to obtain the state-dependent weightings of HMM likelihoods. In this approach, the MLP is trained for phoneme classification, and then the output values of the MLP are used as the state-dependent weightings. Applying the MLP outputs to the state-dependent weightings improves the performance of the conventional HMM without state-dependent weightings. However, in order to further improve the discriminability of competing classes, the discriminative training of the state-dependent weightings is performed by computing the gradient of the optimization criterion for the state-weighted HMM with respect to the MLP parameters. The proposed algorithm reduces the error rate considerably as compared with the conventional HMM in speaker-independent continuous speech recognition.
引用
收藏
页码:79 / 89
页数:11
相关论文
共 21 条
[1]   A THEORY OF ADAPTIVE PATTERN CLASSIFIERS [J].
AMARI, S .
IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS, 1967, EC16 (03) :299-+
[2]  
Bahl L., 1986, INT C ACOUSTICS SPEE, P49
[3]  
BAHL LR, 1988, APR P IEEE INT C AC, P493
[4]  
Baum L.E., 1972, Inequalities III: Proceedings of the Third Symposium on Inequalities, page, V3, P1
[5]   GLOBAL OPTIMIZATION OF A NEURAL NETWORK-HIDDEN MARKOV MODEL HYBRID [J].
BENGIO, Y ;
DEMORI, R ;
FLAMMIA, G ;
KOMPE, R .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (02) :252-259
[6]   LINKS BETWEEN MARKOV-MODELS AND MULTILAYER PERCEPTRONS [J].
BOURLARD, H ;
WELLEKENS, CJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (12) :1167-1178
[7]  
Bourlard H. A., 1994, Connectionist speech recognition: a hybrid approach
[8]  
CERF PL, 1994, IEEE T SPEECH AUDIO, V2, P185
[9]  
CHANG PC, 1992, P IEEE ICASSP 92, P493
[10]  
CHOU W, 1993, APR P IEEE INT C AC, P652