Evolutionary Algorithm for Microphone Array Optimization

Abstract

This paper presented a genetic algorithm (GA) to optimize element placements of microphone array with the purpose of maximizing beamforming SNR for given possible distribution of sound sources. A function based on relationship between statistical geometry descriptors and array performance matrices was applied as the objective function of GA. Optimization experiments of 1D linear array and 2D planar array were performed to demonstrate that this algorithm can effectively sort out superior arrays with significant SNR improvements over randomly generated arrays and regular arrays. High successful rate, rapid convergence speed, and fast processing time observed in all the experiments demonstrate the feasibility of this algorithm as a practical tool for microphone array design.