English

应用科学学报 ›› 1997, Vol. 15 ›› Issue (1): 55-60.

• 论文 • 上一篇    下一篇

自组织特征映射神经网络用于语音识别的研究

胡光锐, 吴硕   

  1. 上海交通大学
  • 收稿日期:1995-09-16 出版日期:1997-03-31 发布日期:1997-03-31
  • 作者简介:胡光锐:教授,上海交通大学电子工程系,上海 200052
  • 基金资助:
    国家攀登计划认知科学(神经网络)重大关键项目

THE STUDY OF SPEECH RECOGNITION USING SOM NEURAL NETWORK

HU GUANGRUI, WU SUO   

  1. Shanghai Jiao-tong University, Shanghai 200030
  • Received:1995-09-16 Online:1997-03-31 Published:1997-03-31

PDF

69

被引次数

15

摘要： 该文提出了一种优化的自组织学习算法。基于自组织特征映射(SOM)神经网络和隐马尔柯夫模型(HMM)法,组成了一种新的语音识别系统,该系统采用SOM网络作为矢量量化器。SOM网络经过优化的自组织学习算法训练后,再用K均值聚类算法对其进行调整。实验结果表明,该文提出的语音识别方法确实能提高系统的识别率。

关键词: 语音识别, 信号处理, 语音处理

Abstract: An optimal self-organization learning algorithm is presented in this paper. A new speech recognition system, which is based on the basis of SOM/HMM principles, bas been provided. In the system, the SOM networks are used as vector quantifier (VQ). After trained by the optimal self-organization algorithm, the SOM networks are adjusted by K-means clustering algorithm. experimental results showed that the new speech recognition method introduced in this paper can raise the recognition accuracy of the system.

Key words: speech recognition, neural networks, speech processing