基于Teager能量算子的语音激活检测  

Voice Activity Detection Based on Teager Energy Operator

作　　者：陈明义[1] 黎华[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《重庆工学院学报》2007年第19期112-114,共3页Journal of Chongqing Institute of Technology

基　　金：湖南省自然科学基金资助项目(05JJ40128)

摘　　要：针对大多数语音激活检测(VAD)方法在低信噪比情况下性能急剧恶化的情况,提出了一种基于Teager能量算子(TEO)的语音激活检测方法.它能结合语音增强技术,应用Teager能量算子进行自适应门限判决.实验结果表明,在低信噪比的情况下,该方法能够随着环境自适应门限,具有较高的准确率和稳定性,简单有效.According to worsened performances of most voice activity detection methods at very low SNR, a new voice activity detection algorithm based on Teager energy operator （TEO） is presented, which can combine speech enhancement technology with Teager energy operator to conduct adaptive threshold judgments. The experimental results prove that the new algorithm is threshold adaptive to environment, simple and efficient, and possesses good performance and stability in a very low SNR environment.

关 键 词：语音激活检测 TEAGER能量算子 自适应门限 

分 类 号：TN912[电子电信—通信与信息系统]