改进的减谱法在语音增强中的应用  

Application of Improved Spectral Subtraction Method to Speech Enhancement

作　　者：黄亚娟[1] 郑林[2] 

机构地区：[1]江苏省产品质量监督检验研究院 [2]河海大学计算机与信息学院

出　　处：《计算机与现代化》2011年第10期31-33,36,共4页Computer and Modernization

摘　　要：为消除语音信号中噪声,改善语音质量,本文提出一种改进的减谱法。首先根据每帧的功率谱动态调整谱减系数,然后通过维纳滤波法把各种噪声变换为类似白噪声的噪声,最后用原减谱法把该噪声去除。实验证明,该方法有较好的去噪效果。In order to remove noise from a speech and improve the speech quality,this paper presents an improved spectral subtraction method.The method first dynamically adjusts spectral subtraction coefficient according to the power spectrum of each speech frame,then transforms all kinds of noises to the noises similar to white noise by Weiner filter,and finally removes the noises by the traditional spectral subtraction method.Experimental results demonstrate that the proposed method is much effective on removing noise.

关 键 词：语音噪声 信噪比 语音增强 减谱法 维纳滤波 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]