| 一种改进的基于子带谱熵的语音激活检测方法 |
| |
| 引用本文： | 宋喆,张德民,张天骐. 一种改进的基于子带谱熵的语音激活检测方法[J]. 重庆邮电学院学报(自然科学版), 2009, 0(6) |
| |
| 作者姓名： | 宋喆 张德民 张天骐 |
| |
| 作者单位： | 重庆邮电大学信号与信息处理重庆市重点实验室; |
| |
| 基金项目： | 国家自然科学基金—中物院NSAF联合基金项目(10776040); 国家自然科学基金项目(60602057); 信号与信息处理重庆市市级重点实验室建设项目(CSTC,2009CA2003); 重庆市科委自然科学基金项目(CSTC,2006BB2373); 重庆市教委自然科学基金项目(KJ060509,KJ080517)资助 |
| |
| 摘 要： | 语音信号的激活检测(voice activity detection,VAD)是变速率语音编码的关键技术,用来检测通信时是否有语音片存在。在有噪环境下对语音信号的激活检测是非常重要而困难的。对传统子带谱熵算法进行了改进,提出了一种能够用于语音激活检测的新算法。该算法利用语音谱熵和噪声谱熵分布的不同,将信号的数字特征(方差、均值等)与传统子带谱熵相结合,用于区分语音段和非语音段。计算机仿真结果表明,在高斯白噪声环境下,改进后的子带谱熵算法能很好地区分说话人的语音段和非语音段,在某种程度上解决了传统语音激活检测算法结构复杂、参数难调、易受噪声影响等问题。
|
| 关 键 词： | 变速率语音编码 激活检测 子带谱熵 统计特性 信噪比 |
An improved voice activity detection algorithm based on band-partitioning spectral entropy |
| |
| SONG Zhe,ZHANG De-min,ZHANG Tian-qi. An improved voice activity detection algorithm based on band-partitioning spectral entropy[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Sciences Edition), 2009, 0(6) |
| |
| Authors: | SONG Zhe ZHANG De-min ZHANG Tian-qi |
| |
| Affiliation: | SONG Zhe,ZHANG De-min,ZHANG Tian-qi(Chongqing Key Lab of Signal , Information Processing,Chongqing University of Posts , Telecommunications,Chongqing 400065,P.R.China) |
| |
| Abstract: | Voice activity detection(VAD) is the key technology of variable rate speech coding to distinguish the speech sentences from non-speeches.Voice activity detection is important but difficult in noisy environments.Hence,an improved spectral entropy algorithm was introduced into the voice activity detection.By using the different distribution feature between the speech entropy and non-speeches entropy,the spectral entropy was combined with the statistics feature to distinguish the speech sentences from non-spee... |
| |
| Keywords: | variable rate speech coding activity detection spectral entropy statistics feature signal to noise ratio |
| 本文献已被 CNKI 等数据库收录！ |
|
