| 自组织特征映射神经网络用于语音识别的研究 |
| |
| 引用本文： | 胡光锐,吴硕.自组织特征映射神经网络用于语音识别的研究[J].应用科学学报,1997(1). |
| |
| 作者姓名： | 胡光锐 吴硕 |
| |
| 作者单位： | 上海交通大学 |
| |
| 基金项目： | 国家攀登计划认知科学（神经网络）重大关键项目 |
| |
| 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，语音处理，信号处理 |
THE STUDY OF SPEECH RECOGNITION USINGSOM NEURAL NETWORK |
| |
| HU GUANGRUI WU SUO.THE STUDY OF SPEECH RECOGNITION USINGSOM NEURAL NETWORK[J].Journal of Applied Sciences,1997(1). |
| |
| Authors: | HU GUANGRUI WU SUO |
| |
| 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 |
| |
| Keywords: | speech recognition neural networks speech processing |
| 本文献已被 CNKI 等数据库收录！ |
