| 语音端点检测方法的分析与实现 |
| |
| 引用本文： | 马道钧,陈天策,高婕. 语音端点检测方法的分析与实现[J]. 北京电子科技学院学报, 2007, 15(4): 66-69 |
| |
| 作者姓名： | 马道钧 陈天策 高婕 |
| |
| 作者单位： | 北京电子科技学院,北京,100070;北京电子科技学院,北京,100070;北京电子科技学院,北京,100070 |
| |
| 摘 要： | 本文在研究短时能量和短时过零率两种语音端点检测基本算法的基础上,编程实现了双门限的端点检测;并进一步根据小波变换的原理,利用小波变换和信号频域统计特性来精确地进行端点检测;最后,在研究了倒谱的相关理论基础上,实现了将语音数据进行倒谱变换,通过计算倒谱距离,在具有一定背景噪声环境下进行端点检测的实验.
|
| 关 键 词： | 端点检测 双门限 小波变换 倒谱 |
| 文章编号： | 1672-464(2007)04-0066-04 |
| 修稿时间： | 2007-08-28 |
Analysis and Implementation of Speech Endpoint Detection |
| |
| MA Dao-jun,CHEN Tian-ce,GAO Jie. Analysis and Implementation of Speech Endpoint Detection[J]. Journal of Beijing Electronic Science & Technology Institute, 2007, 15(4): 66-69 |
| |
| Authors: | MA Dao-jun CHEN Tian-ce GAO Jie |
| |
| Abstract: | Based on short-term energy detection and short-term cross zero rates detection in speech reorganization, the paper presents two-threshold endpoint detection.In addition, an accurate speech segmentation algorithm is achieved with the wavelet transform and statistics signal frequency domain characteristics. using cepstrum transform and cepstrum distance with the background noise, the paper achieved the speech segmentation algorithm. |
| |
| Keywords: | speech endpoint two-threshold endpoint detection wavelet transform cepstrum |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
