经时频掩码的欠定混叠信号的盲提取  

Blind extraction of underdetermined mixtures via time-frequency mask

作　　者：肖明[1] 高峰[2] 孙功宪[2] 谢胜利[2] 

机构地区：[1]广东石油化工学院广东省石化装备故障诊断重点实验室,广东茂名525000 [2]华南理工大学电子与信息学院,广东广州510640

出　　处：《通信学报》2012年第8期77-84,共8页Journal on Communications

基　　金：国家自然科学基金资助项目(61003170;60974072);国家重点基础研究发展计划基金资助项目(2010CB731800);中国博士后科学基金资助项目(20100470920);茂名市科技计划基金资助项目(2011B01041)~~

摘　　要：针对欠定非完全稀疏信号的盲源估计问题,提出了一个新颖的盲提取算法。算法融合非完全稀疏信号的盲提取算法和DUET方法,先利用已估计的混叠矩阵计算源信号的提取矢量和源方向的法矢量,再经线性变换更新混叠信号和混叠矩阵,后采用时频掩码方法恢复源信号。几个语音信号的实验显示算法的性能和实用性。For blind source estimation problem of underdetermined and non-completely sparse signals, a novel blind extraction algorithm was proposed. The algorithm combined the non-completely sparse blind extraction algorithm with the DUET approach. It computed firstly the extraction vector of source and the normal vector of source direction, and then renewed the mixtures and the mixing matrix using a linear transform, and recoverd the source using time-frequency mask method finally. Several speech signal experiments demonstrate its performance and practical.

关 键 词：欠定盲信号分离 稀疏成分分析 时频掩码 盲提取 

分 类 号：TN911.23[电子电信—通信与信息系统]