Helsinki University of Technology    

Karvanen, J., Eriksson, J., Koivunen, V.

Pearson system based method for blind separation

In this paper a new approach for Blind Source Separation (BSS) is introduced. The Pearson system is employed for modeling source distributions. The major benefit of the Pearson system is that it also takes into account the skewness of the distributions. We briefly review the Pearson system and study how its parameters may be estimated. A BSS method combining Pearson system based on the maximum likelihood approach and fixed contrast functions is presented and algorithms for its maximization are proposed. The simulation examples illustrate that the proposed method reliably separates the sources in situations where some widely used BSS methods may perform poorly.