一种低信噪比环境下的语音端点检测方法研究  

Research on Voice Endpoint Detection in Low SNR Status

作　　者：周晓海[1] 王民[1] 毛力[2] 

机构地区：[1]西安建筑科技大学信息与控制工程学院,陕西西安710055 [2]西北工业大学,陕西西安710068

出　　处：《现代电子技术》2009年第10期119-121,共3页Modern Electronics Technique

基　　金：陕西省自然科学基金资助项目(2005F50)

摘　　要：传统的端点检测算法常以短时平均能量、短时平均过零率等特征作为判决参数,但是这些方法在实际应用中,特别是强背景噪声环境下,准确率下降。为此,在利用帧间的倒谱系数距离作为判决方法的基础上,提出改进方法。首先用加权功率谱减法降噪,然后直接计算各帧的倒谱系数相对于原点的距离,再根据预设的判决门限进行判决。降低了因对应系数异号而导致计算帧间倒谱系数距离时产生误判的可能。实验表明,该算法能在低信噪比环境下有效地检测出语音信号的起始位置。Short- time average energy and short- time zero- crossing rate are introduced in traditional voice endpoint detection methods. But in practical environment, these methods are not accurate, especially in this environment where has powerful background noise. Therefore,an improved method based on computing the distance of linear prediction cepstral coefficients between the several frames is proposed. First, using power spectral subtraction to lowen noise, then directly computing the distance of linear prediction cepstraI coefficients relative to origin, and judge it according to threshold that decided beforehand. This method can efficiently lowen the probability of false judgement caused by the different sign of corresponding coefficients between the frames. The experiment result shows that the method can detect voice efficiently in low SNR status.

关 键 词：语音端点检测 门限 功率谱减法 LPC倒谱系数 

分 类 号：TN912[电子电信—通信与信息系统]