Optimization of Artificial Neural Network for Speaker Recognition using Particle Swarm Optimization
Rita Yadav1, Danvir Mandal2
1Rita Yadav, Student (M. Tech, Electronics and Communication Engineering), Punjab Technical University/ Institute of Engineering & Technology, Bhadda (Ropar), Punjab, India.
2Danvir Mandal, Assistant Professor, Electronics and Communication Engineering, Punjab Technical University/ Institute of Engineering & Technology, Bhadda (Ropar), Punjab, India.
Manuscript received on June 18, 2011. | Revised Manuscript received on June 28, 2011. | Manuscript published on July 05, 2011. | PP: 80-84 | Volume-1 Issue-3, July 2011. | Retrieval Number: C067061311
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper proposes a particle swarm optimization (PSO) based optimization technique for Artificial Neural Network weights optimization for speaker recognition. PSO is a search algorithm, in which each potential solution is seen as a particle with a certain velocity flying through the problem space. The particle swarms find optimal regions of the complex search space through the interaction of individuals in the population. PSO is attractive for optimization in that particle swarms will discover best optimized value as they fly within the subset space. Combining the ANN and PSO algorithms improves the performance as compared to that ANN alone.
Keywords: Artificial Neural Network (ANN), Feature Extraction, Matlab, Mel Frequency Cepstral Coefficient, Particle Swarm Optimization, Speaker Recognition.