A practical Approach Based on Gaussianization for Post-Nonlinear Underdetermined BSS

摘要：

This work deals with the Blind Source Separation (BSS) problem in presence of more sources than sensors and Post-Nonlinear (PNL) mixing. The interest on the subject is increased by the fact that very few related contributions have appeared in the literature so far. The proposed method is made of three separate steps: compensation of nonlinearity (based on the Gaussianization concept), mixing matrix recovery and final unknown source estimation. The first one has been already considered for nonlinear complete BSS, but not in the overcomplete case, whereas the latter two represent the typical twostep approach in underdetermined BSS. Performed computer simulations have shown the effectiveness of the idea, even in presence of strong nonlinearities and synthetic mixture of real world data (like speech signals).

作者: Stefano Squartini Alessandro Bastari Francesco Piazza

作者单位: A3Lab-DEIT Universita Politecnica delle Marche Via Brecce Bianche 31, 60131, Ancona, Italy

会议类型: 国际会议

会议名称: 2006 International Conference on Communications,Circuits and Systems(第四届国际通信、电路与系统学术会议)

会议地点: 广西桂林

会议语种:英文

页码: 528-532

在线出版日期: 2006-06-25（万方平台首次上网日期，不代表论文的发表时间）