基于动态特性的D-LTSV语音端点检测方法  

D-LTSV Voice Activity Detection Method Based on Dynamic Feature

作　　者：赵欢[1] 冯璐[1] 陈佐[1] 张希翔[1] 

机构地区：[1]湖南大学信息科学与工程学院,长沙410082

出　　处：《计算机工程》2014年第12期277-281,共5页Computer Engineering

基　　金：国家自然科学基金资助面上项目(61173106)

摘　　要：端点检测是语音信号处理的一个关键环节。为提高语音在低性噪比以及非平稳噪声环境下的端点检测性能,在长时信号变化特征(LTSV)的基础上提出一种新的D-LTSV语音端点检测方法。采用Bartlett-Welch方法估计语音谱,分析语音谱在长时域上的熵,利用倒谱的动态特性分析方法提取连续帧熵值的动态变化特征。实验结果表明,D-LTSV综合考虑了语音的非平稳性和帧间非平稳性的动态变化情况,具有比LTSV更好的分辨能力,特别是在低性噪比和非平稳噪声的环境下,D-LTSV的分辨能力提升了50.77%,能够准确地进行端点检测,具有更强的鲁棒性。Voice Activity Detection（ VAD） is a critical step for speech processing. In order to improve the performance of VAD in low Signal-to-noise Ratio（SNR） and nonstationary noise,this paper proposes a novel D-Long-term Signal Variability（ LTSV） method based on LTSV for VAD. It uses the Bartlett-Welch method to estimate the signal spectrum, analyzes the entropy on the signal spectrum,and utilizes the analytical method of dynamic features used in the cepstrum to extract dynamic features of the entropy. D-LTSV takes into account the degree of nonstationarity of the signal and the dynamic changes between the frames. Compared with LTSV, experimental result shows that D-LTSV owns more discriminative power which is improved by 50 . 77 percent in low SNR and nonstationary noise and makes VAD more robust and more accurate.

关 键 词：语音端点检测 语音谱 长时特征 动态特性 熵 分辨力 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]