| 改进的T-S模糊神经网络在语音识别中的应用 |
| |
| 引用本文： | 王鹏,张雪英. 改进的T-S模糊神经网络在语音识别中的应用[J]. 计算机工程与应用, 2009, 45(4): 246-248. DOI: 10.3778/j.issn.1002-8331.2009.04.072 |
| |
| 作者姓名： | 王鹏 张雪英 |
| |
| 作者单位： | 太原理工大学 信息工程学院，太原 030024 |
| |
| 基金项目： | 国家自然科学基金，山西省自然科学基金 |
| |
| 摘 要： | 给出一种改进的具有四层网络结构的T-S模糊神经网络算法，通过在隶属度上加入一个与输入维数有关的补偿因子，使其能够应用到语音识别系统中，并解决了由输入维数过大而引起的规则灾问题。实验结果表明改进的T-S模糊神经网络能够应用于语音识别系统，同时表明该网络的识别率比RBF网络高，并且鲁棒性较好。
|
| 关 键 词： | 模糊 神经网络 语音识别 |
| 收稿时间： | 2008-01-02 |
| 修稿时间： | 2008-3-18 |
Improved T-S fuzzy neural network in application of speech recognition system |
| |
| WANG Peng,ZHANG Xue-ying. Improved T-S fuzzy neural network in application of speech recognition system[J]. Computer Engineering and Applications, 2009, 45(4): 246-248. DOI: 10.3778/j.issn.1002-8331.2009.04.072 |
| |
| Authors: | WANG Peng ZHANG Xue-ying |
| |
| Affiliation: | College of Information Engineering，Taiyuan University of Technology，Taiyuan 030024，China |
| |
| Abstract: | An improved T-S fuzzy neural network with four layers network structure is introduced.This algorithm adds a compen-sated factor interrelated with the input dimensions on the membership degree,which can be applied into the speech identification system.In the meanwhile it also solves the "regulation disaster"problems caused by the intensive input dimensions.The experi-ment results show the improved T-S fuzzy neural network is applied to speech recognition system,and the recognition ratio of this network is hi... |
| |
| Keywords: | fuzzy neural network speech recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
