| 嘈杂环境下语音信号端点检测方法研究 |
| |
| 引用本文： | 冀常鹏,高茉.嘈杂环境下语音信号端点检测方法研究[J].成都信息工程学院学报,2011,26(3):283-287. |
| |
| 作者姓名： | 冀常鹏 高茉 |
| |
| 作者单位： | 辽宁工程技术大学电子与信息工程学院,辽宁葫芦岛,125105 |
| |
| 摘 要： | 提出了一种嘈杂环境下语音信号端点检测方法。采用基于短时能量和短时过零率的双门限端点检测算法，不但可以减少语音数据的存储量及处理时间，而且能排除无语音段的干扰噪声，从而确保定位的精准性，避免包含噪声信号和丢失语音信号。可以将语音信号同背景噪声分离出来，有效地避免静音段或噪声段的干扰，提高定位估计的性能。仿真实验取得了良好的效果，表明该方法具备一定的可行性。
|
| 关 键 词： | 端点检测 短时能量 短时过零率 短时平均幅度 |
Research on Speech Endpoint Detection in Noisy Background |
| |
| JI Chang-peng
,
GAO Mo.Research on Speech Endpoint Detection in Noisy Background[J].Journal of Chengdu University of Information Technology,2011,26(3):283-287. |
| |
| Authors: | JI Chang-peng GAO Mo |
| |
| Institution: | (School of Electronic and Information Engineering,Liaoning Technical University,Huludao 125105,China) |
| |
| Abstract: | A method for speech signal endpoint detection under noise environment was presented. In the method, use double-threshold algorithm based on short-time energy and short-time zero-crossing rate. This algorithm can not only reduce data memory capacitance and processing time, but also eliminate interference of soundlessness, ensure accuracy of location, avoid including noise signal and losing speech signal. Speech signal can be separated from background noise. Avoiding interference of silence period and noise section effectively, improving estimation performance. The simulation results show the experiment achieves good results, and verifies the feasibility of this method. |
| |
| Keywords: | endpoint detection short time energy short time zero-crossing rate double-threshold algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
