| 基于子带二次谱熵的语音端点检测 |
| |
| 引用本文： | 朱建伟,孙水发,但志平,雷帮军.基于子带二次谱熵的语音端点检测[J].微电子学与计算机,2011,28(3):77-80. |
| |
| 作者姓名： | 朱建伟 孙水发 但志平 雷帮军 |
| |
| 作者单位： | 1. 三峡大学,智能视觉与图像信息研究所,湖北,宜昌,443002;三峡大学,电气与新能源学院,湖北,宜昌,443002
2. 三峡大学,智能视觉与图像信息研究所,湖北,宜昌,443002 |
| |
| 基金项目： | 国家自然科学基金项目，湖北省自然科学基金项目，湖北省教育厅重大项目，湖北省高等学校优秀中青年科技创新团队计划项目，湖北省教育厅中青年项目，宜昌市科学技术研究与开发项目 |
| |
| 摘 要： | 为了提高在强噪声环境下语音端点检测的准确度,提出基于子带二次谱熵的端点检测算法.该算法把子带二次谱熵作为端点检测新的特征参数,首先计算每帧语音信号的二次谱,再多子带分析,计算二次谱熵;引入顺序统计滤波对二次谱熵平滑处理;将有限状态机判别方法与子带二次谱熵相合,形成新的语音/噪声判别算法,有效地解决单门限法易出现的两类误判.实验表明:与传统的两种方法相比,提出的端点检测算法具有准确性高、抗噪性强等优点.
|
| 关 键 词： | 端点检测 子带二次谱熵 有限状态机 顺序统计滤波 |
Voice Activity Detection Based on Sub-band Reprocessed Pectrum Entropy |
| |
| ZHU Jian-wei,SUN Shui-fa,DAN Zhi-ping,LEI Bang-jun.Voice Activity Detection Based on Sub-band Reprocessed Pectrum Entropy[J].Microelectronics & Computer,2011,28(3):77-80. |
| |
| Authors: | ZHU Jian-wei SUN Shui-fa DAN Zhi-ping LEI Bang-jun |
| |
| Affiliation: | ZHU Jian-wei1,2,SUN Shui-fa1,DAN Zhi-ping1,LEI Bang-jun1(1 Institute of Intelligent Vision and Image Information,China Three Gorges University,Yichang 443002,China,2 College of Electrical Engineering and New Energy Technology,China) |
| |
| Abstract: | Voice activity detection(VAD) in strong noise environments is improved by an algorithm based on subband reprocessed spectrum entropy(BRSE).As a new feature parameter for VAD,the reprocessed spectrum is calculated firstly,and reprocessed spectrum entropy is then calculated with multi-sub-band analysis.The order statistics filter is selected to smooth the BRPE.A new voice / noise discrimination algorithm is proposed by combining the finite state machine(FSM) with BRSE.The misdetections caused by single-thresh... |
| |
| Keywords: | voice activity detection subband reprocessed power spectrum entropy finite state machine order statistics filter |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
