基于M估计的有效成比例仿射投影算法  

Efficient proportionate affine projection algorithm based on M-estimate

作　　者：闵亮文 张家树[1] 

机构地区：[1]西南交通大学信号与信息处理重点实验室,四川成都610031

出　　处：《计算机工程与设计》2015年第7期1997-2000,F0003,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(61271341);四川省基础研究发展计划基金项目(2013JY0036)

摘　　要：在回声消除中,针对回声路径具有稀疏性的优势,有学者提出基于μ准则记忆的改进型成比例仿射投影算法(μ-MIPAPA),但该算法抗脉冲干扰性能较差。为此将稳健估计中的M估计应用于该算法,提出一种基于M估计μ准则记忆的改进型成比例仿射投影算法(μ-MMIPAPA)。为使算法具有更好的稳态性能,采用改良的Huber M估计函数,改进阈值参数的选取方式。有色输入下的稀疏回声信道辨识结果表明了μ-MMIPAPA的良好稳态性能和抗脉冲干扰性能。For echo cancellation,theμ-law memory improved proportionate affine projection algorithm（μ-MIPAPA）has been proposed to take advantage of the sparseness of the echo path.However,the algorithm has poor performance on combating impulsive interference.The M-estimate of robust estimates was applied to the algorithm,and aμ-law memory improved proportionate affine projection algorithm based on M-estimate（μ-MMIPAPA）was presented.To make the algorithm has better steady-state perfor-mance,a modified Huber M estimation function was used and the way of the threshold parameter selection was improved.The perfor-mance of the proposed algorithm was verified by the simulation of sparse echo channel identification in colored input.

关 键 词：回声消除 仿射投影算法 脉冲干扰 M-估计 有色输入 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置]