Comparison of Different Parameters used in GMM Based Automatic Speaker Recognition
Archana Shende1, Subhash Mishra2, Shiv Kumar3
1Archana Shende, Department of Electronics and Communication (M.Tech. Scholar), Technocrat Institute of Technology-Bhopal (M.P.), India.
2Prof. Subhash Mishra, Department of Electronics and Communication, Technocrat Institute of Technology-Bhopal (M.P.), India.
3Prof. Shiv Kumar, Asst. Professor, Department of Information Technology, Technocrat Institute of Technology-Bhopal (M.P.), India.
Manuscript received on May 20, 2011. | Revised Manuscript received on June 10, 2011. | Manuscript published on July 05, 2011. | PP: 14-18 | Volume-1 Issue-3, July 2011. | Retrieval Number: C043051311
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: The performance of Speaker recognition systems has improved due to recent advances in speech processing techniques but there is still need of improvement. In this paper we present the comparison of different parameters used in automatic speech recognition system to increase the accuracy of the system. The main goal here is a detailed evaluation of the parameters used in Automatic speech recognition system such as window type, MFCC frame size, number of Gaussian mixtures and GMM & VQ/GMM technique .In this paper we propose a decision function by using vector quantization techniques to decrease the training model for GMM in order to reduce the processing time.
Keywords: Gaussian Mixture Model (GMM), Mel Frequency Cepstral Coefficient (MFCC), Speaker Identification (SI), Speaker Verification (SV), Vector Quantization (VQ).