| 基于全监督算法RBF神经网络的语音识别 |
| |
| 引用本文： | 侯雪梅. 基于全监督算法RBF神经网络的语音识别[J]. 西安邮电学院学报, 2011, 16(1): 87-90 |
| |
| 作者姓名： | 侯雪梅 |
| |
| 作者单位： | 西安邮电学院,自动化学院,陕西,西安,710121 |
| |
| 摘 要： | 利用RBF神经网络,采用全监督训练算法,实现基于RBF神经网络的抗噪语音识别系统。与传统的K-均值聚类算法相比较,采用全监督训练算法可避免隐含层节点中心容易对初始值敏感的缺点,且能使RBF网络具备更强的分类能力。实验结果表明,在不同的信噪比下,全监督训练算法比传统聚类算法有更高的识别率。
|
| 关 键 词： | 语音识别 RBF神经网络 全监督 |
Speech recognition based on RBF neural network with entire-supervised algorithm |
| |
| HOU Xue-mei. Speech recognition based on RBF neural network with entire-supervised algorithm[J]. Journal of Xi'an Institute of Posts and Telecommunications, 2011, 16(1): 87-90 |
| |
| Authors: | HOU Xue-mei |
| |
| Affiliation: | HOU Xue-mei(School of Automation,Xi'an University of Posts and Telecommunications,Xi'an 710121,China) |
| |
| Abstract: | Considering the actuality of current speech recognition and the characteristic of RBF neural network,a noise-robust speech recognition system based on RBF neural network is proposed with the entire-supervised algorithm.If the traditional K-means algorithm is employed,there is a flaw that the node center of hidden layer is always sensitive to the initial value,but if the entire-supervised algorithm is used,the flaw will not turn up,and the classification ability of RBF network will be enhanced.Experimental r... |
| |
| Keywords: | speech recognition RBF neural network entire-supervised |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
