小波分析和粒子群优化神经网络的语音端点检测  

Wavelet Analysis and the Neural Network of Particle Swarm Optimization for Speech Endpoints Detection

作　　者：陈雪芳[1] 

机构地区：[1]东莞理工学院计算机学院,广东东莞523808

出　　处：《微电子学与计算机》2013年第9期94-97,共4页Microelectronics & Computer

基　　金：国家自然科学基金(2000927001);东莞市高校科研机构科技计划项目(2011108102016)

摘　　要：为了提高语音端点检测的适应性和鲁棒性,提出一种小波分析和粒子群优化神经网络(WA-PSO-BP)的语音端点检测算法.首先利用小波分析提取语音信号的特征量,然后将特征量作为输入BP神经网络进行学习,并采用粒子群算法优化BP神经网络参数,从而建立语音端检测模型.仿真结果表明,WA-PSO-BP提高了语音端点检测正确率,有效降低了虚检率和漏检率.这说明WA-PSO-BP是一种可行性较高,环境适应性较强的语音检测算法.In order to improve the adaptability and robustness of speech endpoint detection, this paper proposes a speech endpoint detection method base on WA-PSO-BP. Firstly, the feature of speech signals are extracted by wavelet analysis; then the features are input to BP neural network to build the speech endpoints detection model in which the BP neural network＇ s parameters are optimized by particle swarm optimization algorithm, The experiments results show that the proposed method has improved the detection rate, and it has better adaptability and robustness. WA-PSO-BP has high reliability makes it suitable for application in different kinds of environments.

关 键 词：小波分析 神经网络 语音端点 粒子群优化算法 特征选择 

分 类 号：TN91[电子电信—通信与信息系统]