A New Design And Implementation On Convolution Blind Source Seperation

Abstract

Brief presents an efficient very-large-scale integration architecture design for convolutive blind source separation (CBSS). The CBSS separation network derived from the information maximization (Infomax) approach is adopted. The proposed CBSS chip design consists mainly of Infomax filtering modules and scaling factor computation modules. In an Infomax filtering module, input samples are filtered by an Infomax filter with the weights updated by Infomax-driven stochastic learning rules. As for the scaling factor computation module, all operations including logistic sigmoid are integrated and implemented by the circuit design based on a piecewise-linear approximation scheme. The proposed prototype chipis implemented via a semicustom design using90-nmCMOS technology on a die size of approximately 0.54×0.54 mm2.