This work presents an efficient VLSI architecture design for convolutive blind source separation (CBSS). The CBSS separation network derived from 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 chip is implemented via a semi-custom design using 90 nm CMOS technology on a die size approximately 0.54×0.54 mm2