Blind separation of sources that have spatiotemporal variance dependencies

被引：24

作者：

Hyvärinen, A

Hurri, J

机构：

[1] Univ Helsinki, Dept Comp Sci, Helsinki Inst Informat Technol, Basic Res Unit, FIN-00014 Helsinki, Finland

[2] Aalto Univ, Neural Networks Res Ctr, FIN-02150 Espoo, Finland

来源：

SIGNAL PROCESSING | 2004年 / 84卷 / 02期

关键词：

independent component analysis; blind source separation; dependent component analysis; higher-order cumulants;

D O I：

10.1016/j.sigpro.2003.10.010

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In blind source separation methods, the sources are typically assumed to be independent. Some methods are also able to separate dependent sources by estimating or assuming a parametric model for their dependencies. Here, we propose a method that separates dependent sources without a parametric model of their dependency structure. This is possible by introducing some general assumptions on the structure of the dependencies: the sources are dependent only through their variances (general activity levels), and the variances of the sources have temporal correlations. The method can be called double-blind because of this additional blind aspect: We do not need to estimate (or assume) a parametric model of the dependencies, which is in stark contrast to most previous methods. (C) 2003 Elsevier B.V. All rights reserved.

引用

页码：247 / 254

页数：8