To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Separation of Convolutive Mixtures of Cyclostationary Sources by Reference Contrasts |
|
Author |
K. Sabri, M. Taoufiki, A. Adib, D. Aboutajdine, M. El Badaoui, F. Guillet |
| Citation |
Vol. 6 No. 3 pp. 224-229 |
|
Abstract |
This paper introduces new source separation techniques exploiting the cyclostationarity property of the source signals. Two cyclostationary-based reference contrast functions are presented for convolutive mixtures and cyclostationary signals. Contrary to the major contrasts, any para-unitarity constraint is made on the mixing system. Their maximization enjoys identifiability properties, and aims at delivering outputs satisfying specific properties, such as statistical independence or a cyclostationarity character. Simulation examples are presented to illustrate the effectiveness of this approach in terms of the estimated source variances. |
|
Keywords |
Cyclic statistics, Blind Source Separation, Convolutive mixture, Reference contrast, Cyclostationarity. |
|
URL |
