Automatic Speaker Recognition Based on Mel-Frequency Cepstral Coefficients and Gaussian Mixture Models

This paper investigates the task of SR (Speaker Recognition) for the state-of-the-art techniques. The paper initially presents the technical description of automatic SR, followed by the comparative analysis of a number of methods available for feature extraction and modeling. Based on this analysis...

Full description

Bibliographic Details

Published in:	Mehran University Research Journal of Engineering and Technology
Main Authors:	Sheeraz Memon, Sania Bhatti, Farzana Rauf Abro
Format:	Article
Language:	English
Published:	Mehran University of Engineering and Technology 2013-10-01
Subjects:	Mel Frequency Cepstral Coefficients Gaussian Mixture Models Expectation Maximization Speaker Recognition
Online Access:	http://publications.muet.edu.pk/research_papers/pdf/pdf809.pdf