EFFICIENT FREQUENCY-DOMAIN IMPLEMENTATION OF SPEECH DISTORTION WEIGHTED MULTI-CHANNEL WIENER FILTERING FOR NOISE REDUCTION (FriAmPO1)

Author(s) : Simon Doclo (KU Leuven - Dept. of Electrical Engineering (ESAT-SCD), Belgium) Ann Spriet (KU Leuven - Dept. of Electrical Engineering (ESAT-SCD), Belgium) Marc Moonen (KU Leuven - Dept. of Electrical Engineering (ESAT-SCD), Belgium)

Abstract : A stochastic gradient implementation of a generalised multi-microphone noise reduction scheme, called the Spatially Pre-processed Speech Distortion Weighted Multi-channel Wiener Filter (SP-SDW-MWF), has recently been proposed in [1]. In order to compute a regularisation term in the filter update formulas, data buffers are required in this implementation, resulting in a large memory usage. This paper shows that by approximating this regularisation term in the frequency-domain the memory usage (and the computational complexity) can be reduced drastically. Experimental results demonstrate that this approximation only gives rise to a limited performance difference and that hence the proposed algorithm preserves the robustness benefit of the SP-SDW-MWF over the GSC (with Quadratic Inequality Constraint).

Menu