多尺度小波分解下的自适应语音消噪算法研究  

Study on adaptive speech signal noise cancellation algorithm with multi-scale wavelet decomposition

作　　者：唐建锋[1] 张登玉[1] 罗湘南[1] 

机构地区：[1]衡阳师范学院物理与电子信息科学系,湖南衡阳421008

出　　处：《计算机工程与应用》2009年第23期154-157,共4页Computer Engineering and Applications

基　　金：湖南省自然科学基金No.06JJ50118;衡阳师范学院青年骨干教师资助项目~~

摘　　要：将小波变换的理论引入到自适应语音消噪系统中,分析了多尺度小波分解下的LMS自适应消噪算法(MSWD-LMS)的原理,该算法将输入向量分解到多尺度空间,减小了自适应滤波器输入向量自相关矩阵的谱动态范围;将变步长LMS算法与多尺度小波变换的思想结合,提出了一种新的小波自适应语音消噪算法(MSWD-VSS-LMS),新算法既减少了输入向量自相关矩阵条件数,又克服了固定步长LMS算法在收敛速度与收敛精度方面与步长因子μ的矛盾,获得了更好的语音信号处理的收敛速度和稳定性。仿真结果表明新算法取得了较好的效果。The wavelet transfotan theory is introduced into the adaptive speech signal noise cancellation system.The principle of LMS adaptive speech signal noise cancellation algorithm with multiple-scale wavelet decomposition is analyzed.The MSWD-LMS algorithm converges faster than the elassical LMS algorithm,and the spectrum dynamic range of auto-correlation matrix of the input vector which is decomposed to multiple-scale space is deereased.The variable step size LMS algorithm and the multiplescale wavelet decomposition are merged into the adaptive speech signal noise cancellation system.A novel method is proposed, that is,a LMS adaptive algorithm with Variable Step Size based on Multiple-Scale Wavelet Decomposition（MSWD-VSS-LMS）.The novel algorithm can decrease the conditions of auto-correlation matrix of the input vector,as well as resolve the contradiction that fixed step size cannot result in fast eonvergence speed and low residual error simultaneously.Experimental results demonstrate that the new algorithm has not only better convergence property but also belier stable mean square errors than the former algorithms

关 键 词：自适应语音消噪 最小均方(LMS)算法 变步长 多尺度小波分解 

分 类 号：TN911[电子电信—通信与信息系统]