標題: A speech recognition method based on the sequential multi-layer perceptrons
作者: Chen, WY
Chen, SH
Lin, CJ
交大名義發表
National Chiao Tung University
關鍵字: neural network;generalized probabilistic descent;multi-layer perceptrons;hidden markov models;speech recognition;dynamic programming
公開日期: 1-六月-1996
摘要: A novel multi-layer perceptrons (MLP)-based speech recognition method is proposed in this study. In this method, the dynamic time warping capability of hidden Markov models (HMM) is directly combined with the discriminant based learning of MLP for the sake of employing a sequence of MLPs (SMLP) as a word recognizer. Each MLP is regarded as a state recognizer to distinguish an acoustic event. Next, the word recognizer is formed by serially cascading all state recognizers. Advantages of both HMM and MLP methods are attained in this system through training the SMLP with an algorithm which combines a dynamic programming (DP) procedure with a generalized probabilistic descent (GPD) algorithm. Additionally, two sub-syllable SMLP-based schemes are studied through application of this method toward the recognition of isolated Mandarin digits. Simulation results confirm that the performance of the methods is comparable to a well modeled continuous Gaussian mixture density HMM trained with the minimum error criterion. Not only does the SMLP require less trainable parameters than the HMM system, but the former is more convenient for analysing internal features. With the aid of internal feature selection, discarding the least useful parameters of SMLP without affecting its performance is relatively easy. Copyright (C) 1996 Elsevier Science Ltd
URI: http://dx.doi.org/10.1016/0893-6080(95)00140-9
http://hdl.handle.net/11536/1231
ISSN: 0893-6080
DOI: 10.1016/0893-6080(95)00140-9
期刊: NEURAL NETWORKS
Volume: 9
Issue: 4
起始頁: 655
結束頁: 669
顯示於類別:期刊論文


文件中的檔案:

  1. A1996UT30900008.pdf