Name
Abstract | ||
|---|---|---|
This paper discusses the theoretical foundation of Stone’s BSS (Stone in Neural Comput 13:1559–1574, 2001; Stone in Independent Component Analysis: A Tutorial Introduction, A Bradford Book, London, 2004), and it proposes a novel BSS approach based on second-order statistics of the responses of two different linear filters to source signals. The proposed approach which includes Stone’s BSS as a special case helps us to understand how generalized eigenvalue decomposition (GEVD) concludes separating vectors in Stone’s BSS. It obtains the separating vectors by simultaneous diagonalization of covariance matrices of two different linear filters responses to the mixtures. The two employed linear filters are selected dependent on source signals structures under the assumption that they have different responses to source signals. Here, two FIR filters with coefficients selected in an opposite probabilistic way have been suggested for the proposed BSS. The proposed BSS method has been compared with Stone’s BSS, SOBI and AMUSE over speech and image mixtures in different noise levels. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1007/s11760-010-0161-0 | Signal, Image and Video Processing |
Keywords | DocType | Volume |
Blind source separation, Stone’s BSS, Simultaneous diagonalization, General eigenvalue decomposition | Journal | 5 |
Issue | ISSN | Citations |
3 | 1863-1711 | 2 |
PageRank | References | Authors |
0.38 | 20 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mahdi Khosravy | 1 | 20 | 6.92 |
| Mohammad Reza Asharif | 2 | 17 | 4.69 |
| Katsumi Yamashita | 3 | 82 | 7.77 |