Title: Text independent speaker identification with finite multivariate generalised Gaussian mixture model and k-means algorithm

Authors: V. Sailaja; K. Srinivasa Rao; K.V.V.S. Reddy

Addresses: Department of Electronics & Communication Engineering, GIET, Rajahmundry, India ' Department of statistics, Andhra University, Visakhapatnam, India ' Department of Electronics & Communication Engineering, Andhra University, Visakhapatnam, India

Abstract: In this paper, we propose text independent speaker identification with a finite multivariate generalised Gaussian Mixture Model (GMM) with a k-means algorithm. Each speaker's speech spectra are characterised with a mixture of generalised Gaussian distribution that includes Gaussian and Laplacian distribution as a particular case. Speech analysis is done with the Mel Frequency Cepstral Coefficients (MFCC) extracted from the front end process. Using the EM algorithm and k-means algorithm the model parameters the numbers of acoustic classes associated with each speech spectra are determined. The performance of the proposed algorithm is studied through experimental evaluation and observed that this algorithm outperforms the existing speaker identification algorithm with GMM. It is also observed that this algorithm performs efficiently even with a heterogeneous population with small (less than 2 seconds) utterances.

Keywords: Gaussian mixture model; generalised GMM; MFCC; mel frequency cepstral coefficients; k-means clustering; EM algorithm; speech analysis; text independent speaker identification; speech spectra.

DOI: 10.1504/IJSISE.2013.053419

International Journal of Signal and Imaging Systems Engineering, 2013 Vol.6 No.2, pp.119 - 126

Received: 05 Feb 2011
Accepted: 09 Jan 2012
Published online: 21 Apr 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article