首页 | 本学科首页   官方微博 | 高级检索  
     

基于ICA增强和谱熵的语音端点检测方法
引用本文:覃溪,钟明辉,曹乃文,黄汉明.基于ICA增强和谱熵的语音端点检测方法[J].电声技术,2006(10):49-50,54.
作者姓名:覃溪  钟明辉  曹乃文  黄汉明
作者单位:广西师范大学,物理与电子工程学院,广西,桂林,541004
摘    要:端点检测是语音信号处理过程中非常重要的一步,它的准确性直接影响到语音信号处理的速度和结果。提出了基于ICA(独立分量分析)增强和谱熵的语音端点检测方法。仿真实验表明此方法快速有效,具有较强的抗噪能力,特别适合低信噪比下的端点检测。

关 键 词:独立分量分析  谱熵  端点检测
文章编号:1002-8684(2006)10-0049-02
收稿时间:2006-07-20
修稿时间:2006-07-20

Speech Endpoint Detection Method Based on ICA Enhancement and Spectral Entropy
QIN Xi,ZHONG Ming-hui,CAO Nai-wen,HUANG Han-ming.Speech Endpoint Detection Method Based on ICA Enhancement and Spectral Entropy[J].Audio Engineering,2006(10):49-50,54.
Authors:QIN Xi  ZHONG Ming-hui  CAO Nai-wen  HUANG Han-ming
Affiliation:College of Physics and Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541004, China
Abstract:The endpoint detection which influences the speed and results of speech signals processing directly is a important step for speech signal processing. In this paper, a new speech endpoint detection method based on ICA(Independent Component Analysis) enhancement and spectral entropy is proposed. The simulating results show that the proposed method can detect the endpoint exactly in the low SNR environments.
Keywords:independent component analysis  spectral entropy  endpoint detection
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号