A New Shuffled Sub-swarm Particle Swarm Optimization Algorithm for Speech Enhancement

Abstract

In this paper, we propose a novel algorithm to enhance the noisy speech in the framework of dual-channel speech enhancement. The new method is a hybrid optimization algorithm, which employs the combination of the conventional θ-PSO and the shuffled sub-swarms particle optimization (SSPSO) technique. It is known that the θ-PSO algorithm has better optimization performance than standard PSO algorithm, when dealing with some simple benchmark functions. To improve further the performance of the conventional PSO, the SSPSO algorithm has been suggested to increase the diversity of particles in the swarm. The proposed speech enhancement method, called θ-SSPSO, is a hybrid technique, which incorporates both θ-PSO and SSPSO, with the goal of exploiting the advantages of both algorithms. It is shown that the new θ-SSPSO algorithm is quite effective in achieving global convergence for adaptive filters, which results in a better suppression of noise from input speech signal. Experimental results indicate that the new algorithm outperforms the standard PSO, θ-PSO, and SSPSO in a sense of convergence rate and SNRimprovement.