Improved Particle Swarm Optimization for Dual-Channel Speech Enhancement

Abstract

This paper, proposes an improved particle swarm optimization algorithm for speech enhancement. In the proposed algorithm, the population is divided into two subgroups. One of the subgroups searches the space globally, whereas the other one explores the problem space locally. The proposed algorithm surpasses the standard PSO, by stimulating the inactive particles and local search around the global best. Experimental results indicate that improved particle swarm optimization (IPSO) outperforms the standard particle swarm optimization (SPSO), and gradient-based NLMS algorithm in dual-channel speech enhancement applications.