A Speech Recognition Method Using Competitive and Selective Learning Neural Networks

In this paper,a basic principle called the equidistortion principle for vector clustering is theoretically derived by using Gersho’s asymptotic theory,and a new competitive learning algorithm is prorosed with a selection mechanism,called the CLS(Competitive and Selective Learning)algorithm.Because t...

Full description

Saved in:
Bibliographic Details
Main Author: Hu Guangrui Xu Xiong Yan Yonghong
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 1998-01-01
Series:Tongxin xuebao
Online Access:http://www.joconline.com.cn/zh/article/74373054/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841538589125509120
author Hu Guangrui Xu Xiong Yan Yonghong
author_facet Hu Guangrui Xu Xiong Yan Yonghong
author_sort Hu Guangrui Xu Xiong Yan Yonghong
collection DOAJ
description In this paper,a basic principle called the equidistortion principle for vector clustering is theoretically derived by using Gersho’s asymptotic theory,and a new competitive learning algorithm is prorosed with a selection mechanism,called the CLS(Competitive and Selective Learning)algorithm.Because the selection mechanism enables the system to escape from local minima,the proposed algorithm can obtain better performance without a particular initialization procedure.A new neural network algorithm with competitive learning and multiple safe rejection schemes are proposed in the context of parallel,self organizing,hierarchical neural networks(PSHNN).The input of PSHNN is a subset of the output scores of HMM.The experimental results indicate that the recognition ability of the method based on competitive learning neural network is higher than that of the traditional HMM method.
format Article
id doaj-art-899ef4ab00084cc292290a0338754c28
institution Kabale University
issn 1000-436X
language zho
publishDate 1998-01-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-899ef4ab00084cc292290a0338754c282025-01-14T07:43:30ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X1998-01-0174373054A Speech Recognition Method Using Competitive and Selective Learning Neural NetworksHu Guangrui Xu Xiong Yan YonghongIn this paper,a basic principle called the equidistortion principle for vector clustering is theoretically derived by using Gersho’s asymptotic theory,and a new competitive learning algorithm is prorosed with a selection mechanism,called the CLS(Competitive and Selective Learning)algorithm.Because the selection mechanism enables the system to escape from local minima,the proposed algorithm can obtain better performance without a particular initialization procedure.A new neural network algorithm with competitive learning and multiple safe rejection schemes are proposed in the context of parallel,self organizing,hierarchical neural networks(PSHNN).The input of PSHNN is a subset of the output scores of HMM.The experimental results indicate that the recognition ability of the method based on competitive learning neural network is higher than that of the traditional HMM method.http://www.joconline.com.cn/zh/article/74373054/
spellingShingle Hu Guangrui Xu Xiong Yan Yonghong
A Speech Recognition Method Using Competitive and Selective Learning Neural Networks
Tongxin xuebao
title A Speech Recognition Method Using Competitive and Selective Learning Neural Networks
title_full A Speech Recognition Method Using Competitive and Selective Learning Neural Networks
title_fullStr A Speech Recognition Method Using Competitive and Selective Learning Neural Networks
title_full_unstemmed A Speech Recognition Method Using Competitive and Selective Learning Neural Networks
title_short A Speech Recognition Method Using Competitive and Selective Learning Neural Networks
title_sort speech recognition method using competitive and selective learning neural networks
url http://www.joconline.com.cn/zh/article/74373054/
work_keys_str_mv AT huguangruixuxiongyanyonghong aspeechrecognitionmethodusingcompetitiveandselectivelearningneuralnetworks
AT huguangruixuxiongyanyonghong speechrecognitionmethodusingcompetitiveandselectivelearningneuralnetworks