Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
413048 | Neurocomputing | 2008 | 14 Pages |
Abstract
In blind source separation, the definition of sources has an inherent indeterminacy; any linear transform of a source signal can be considered another form of it. Due to this indeterminacy, the designing of a separator has a certain freedom. This paper proposes an idea for eliminating the indeterminacy, i.e., a principle for uniquely normalizing the separator. The output of the separator based on the principle undergoes the least distortion in the demixing process. The method has some good properties: no signal distortion, no fluctuation for nonstationary sources, and simple implementation.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Kiyotoshi Matsuoka,