一种新的欠定时延混合矩阵估计算法  

A Novel Under-Determined Mixing Matrix Estimation

作　　者：吴嘉诚 何文波 范立 罗丽平 WU Jiacheng;HE Wenbo;FAN Li;LUO Liping(Southwest China Research Institute of Electronic Equipment,Chengdu 610036,China;The 3rd Representative Office of PLA Air Force Equipment Technology Department in Chengdu,Chengdu 610015,China)

机构地区：[1]中国电子科技集团公司第二十九研究所,成都610036 [2]空装成都局驻成都地区第三军代表室,成都610015

出　　处：《电子信息对抗技术》2022年第4期48-52,共5页Electronic Information Warfare Technology

摘　　要：针对欠定时延混合模型下的盲源分离问题,提出一种新的混合矩阵估计算法。该算法利用观测信号在时频域的稀疏特性,通过不同观测信号的短时傅里叶变换系数寻找出只有一个源信号的时频点;最后采用改进的聚类方法估计出混合矩阵。实验仿真表明该算法可以很好地估计出混合矩阵,并且拥有比其它算法更好的估计性能。A novel mixing matrix estimation algorithm is proposed to solve the problem of blind source separation under the under-determined time-delayed mixed model.The sparse characteristics of the observation signals are utilized in time-frequency domain and the time-frequency points are found where only one source exists through the short-time Fourier transform coefficients of different observation signals.Finally,the improved clustering method is used to estimate the mixing matrix.Experimental simulations show that the mixing matrix could be estimated well,the algorithm has better estimation performance.

关 键 词：欠定时延混合模型 盲源分离 混合矩阵 聚类 

分 类 号：TN971.1[电子电信—信号与信息处理]