| 一种基于小波和时频分解的端点检测方法 |
| |
| 引用本文： | 董胡,钱盛友.一种基于小波和时频分解的端点检测方法[J].微计算机信息,2007,23(30):228-229,264. |
| |
| 作者姓名： | 董胡 钱盛友 |
| |
| 作者单位： | 湖南师范大学物理与信息科学学院,长沙,410081 |
| |
| 摘 要： | 提出了一种新的基于小波和时频分解的语音端点检测方法。首先通过小渡分解对舍噪信号进行增强，然后采用Matching pursuits算法对去噪信号进行时频分解．使得信号在时频平面上具有较明显的魏格纳能量分布．最后利用该特点设定合适的门限来进行语音端点检测。实验结果表明，该方法对低信噪比的语音端点检测仍有效。
|
| 关 键 词： | 小波 语音增强 时频分解 端点检测 |
| 文章编号： | 1008-0570（2007）10-3-0228-02 |
| 修稿时间： | 2007-07-032007-09-05 |
A Method of Endpoint Detection Based on Wavelet and Time-frequency Decomposition |
| |
| DONG HU,QIAN SHENGYOU.A Method of Endpoint Detection Based on Wavelet and Time-frequency Decomposition[J].Control & Automation,2007,23(30):228-229,264. |
| |
| Authors: | DONG HU QIAN SHENGYOU |
| |
| Affiliation: | College of Physics and Information Science, Humm Normal University, Changsha, 410081, China |
| |
| Abstract: | A new method of speech endpoint detection based on wavelet and decomposition in time-frequency domain is proposed. Signal containing noise is strengthened through wavelet decomposition, then the reconstructed signal is decomposed by Matching pursuits algorithm in time-frequency domain to obtain apparent Wigner energy distribution. Finally, a suitable threshold is selected to detect the speech endpoint according to these properties. Experimental results demonstrate this approach is effective for low SNR speech endpoint detection. |
| |
| Keywords: | Speech enhancement Wavelet Time-Frequency decomposifion Endpoint detection |
| 本文献已被 维普 万方数据 等数据库收录！ |
