A Comparative Study of Two Different Neural Models for Speaker Recognition Systems
Geeta Nijhawan1, M.K. Soni2
1Ms. Geeta Nijhawan, Deptt. of Electronics and Communications, FET, Mriu, Faridabad, India.
2Dr. M.K. Soni, Executive Director & Dean, FET, Mriu, Faridabad, India.
Manuscript received on May 01, 2012. | Revised Manuscript received on May 28, 2012. | Manuscript Published on June 10, 2012. | PP: 67-72 | Volume-1 Issue-1, June 2012. | Retrieval Number: A120051112 /2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. 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: In recent years there has been a significant amount of work, both theoretical and experimental, that has established the viability of artificial neural networks (ANN’s) as a useful technology for speech recognition. It has been shown that neural networks can be used to augment speech recognizers whose underlying structure is essentially that of hidden Markov models (HMM’s). In this paper, we first give a brief overview of automatic speech recognition (ASR) and then describe the use of ANN’s as statistical estimators. We have compared back propogation (BP) neural network and radial basis function (RBF) network’s performance as applied to the speaker recognition. We have compared the two neural network results by MATLAB simulation. From the quantitative point we have proved that the RBF neural network is more efficient and accurate than BP neural network in speaker recognition, and thus more suitable for practical applications.
Keywords: Speaker recognition system, Linear Predictive Coding (LPC), Neural networks, Mel Frequency Cepstrum Coefficient (MFCC), Back Propagation (BP); Radial Basis Function (RBF).