改进的基于长时谱能量差异和基音比例的语音检测方法  

Improved Voice Activity Detection Based on Long-term Spectral Divergence and Pitch Ratio Features

作　　者：孟一鸣[1] 欧智坚[1] 

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《电讯技术》2013年第8期1039-1043,共5页Telecommunication Engineering

摘　　要：语音检测是语音信号处理的前端,利用长时谱能量差异特征的语音检测无法区分突发噪声和语音,掺杂着突发噪声的语音信号会对语音处理系统带来不良影响。提出了一种基于长时谱能量差异特征和基音比例特征相结合的语音检测方法,该方法的优点是,在利用长时谱能量差异特征基础上引入基音比例特征,从而有效减少了将信号中突发噪声误判为语音的错误。实验显示,该算法能够在多种信噪比环境下取得很好的检测结果。Voice Activity Detection（VAD） is the front-end of speech processing and the VAD algorithm which uses long-term spectral divergence（LTSD） feature can′t discriminate abrupt noise from speech.The speech signal with abrupt noise will adversely affect the speech processing system.This paper proposes a VAD algorithm which combines LTSD feature and pitch ratio feature.The advantage of the algorithm is that by introducing pitch ratio feature,it can effectively reduce the false alarms of taking abrupt noise as speech.Experimental results show that the algorithm achieves good performance for VAD under various signal-to-noise ratios.

关 键 词：语音信号处理 语音检测 长时谱能量差异 基音比例 突发噪声 

分 类 号：TN912.3[电子电信—通信与信息系统]