Adaptive approach to blind source separation with cancellation of additive and convolutional noise

Abstract
In this paper an adaptive approach to cancellation of additive, convolutional noise from many--source mixtures witha simultaneous blind source separation is proposed. Associatedneural network learning algorithms are developed onthe basis of decorrelation principle and energy minimizationof output signals. The reference noise is transformed intoa convolutional one by employing an adaptive FIR filterin each channel. Several models of NN learning processesare considered. In the basic...

This publication has 3 references indexed in Scilit: