噪声中的复信号盲源分离算法  

Blind source separation algorithm for complex signals in noise

作　　者：冯平兴 张洪波 李文翔 Feng Pingxing;Zhang Hongbo;Li Wenxiang(School of Network and Communication Engineering,Chengdu Technological University,Chengdu 611731,China;School of Communication and Information Engineering,Chengdu University of Information Technology,Chengdu 610103,China)

机构地区：[1]成都工业学院网络与通信工程学院,四川成都611731 [2]成都信息工程大学通信工程学院,四川成都610103

出　　处：《电子技术应用》2022年第4期67-70,75,共5页Application of Electronic Technique

基　　金：成都工业学院博士基金科研项目(195076)。

摘　　要：复信号分析是信号处理技术常见的问题之一,在盲信号分离及处理技术中特别是卷积混合问题或频域分析等均需要建立与之相应的复值分析模型。然而在以往的分析中,由于此类问题往往是基于无噪声的约束条件,因此局限了该技术在实际中的应用。针对这一问题,将复值盲源分离问题推广到含噪声的一般环境中。通过分析高斯噪声协方差的一般特征,利用高斯噪声协方差的参数信息,导出了一种在噪声环境下盲源分离的不动点算法,该算法可以在噪声环境中通过观测信号估计与之对应的有效分离矩阵,使得复值信号在噪声环境中混合中仍然能成功分离出源信号。仿真结果表明了所研究方法的可行性与有效性。Complex signal analysis is one of the common problems in signal processing technology.In blind signal separation technology,especially convolution mixing problem or frequency domain analysis,it is necessary to establish the corresponding complex value analysis model.In the previous analysis,such problems are often based on a noise free constraint,which limits the application of this technology in practice.In order to solve this problem,this research extends the complex valued blind source separation to the more general environment that with noise.By analyzing the general characteristics of Gaussian noise and using the parameter information of Gaussian noise covariance,a fixed point algorithm for blind source separation in noisy environment is derived.The algorithm can estimate the corresponding effective separation matrix through observed signals in noisy environment.The simulation results show the feasibility and effectiveness of the proposed method.

关 键 词：盲源分离 复信号处理 高斯噪声 信号恢复 

分 类 号：TN95[电子电信—信号与信息处理]