Authors: Eric Fang; John N. Gowdy
Addresses: Clemson University, 6415 Schmidt Lane Apt B312, El Cerrito, CA 94530, USA ' Clemson University, Riggs Hall, ECE Department, Clemson, SC 29634, USA
Abstract: This paper focuses on developing new algorithms for improving speaker identification accuracy. Forty nine male speakers from the DARPA resource management continuous speech database were used for training and testing. Mel-frequency cepstral coefficients (MFCC) components were used for training and testing. Vector quantisation (VQ) was used for classification. In addition to presenting identification results, this paper shows the error reduction rate relative to a baseline system.
Keywords: speaker identification; mel-frequency cepstral coefficients; MFCC; vector quantization; biometrics; continuous speech.
International Journal of Biometrics, 2013 Vol.5 No.3/4, pp.360 - 369
Received: 11 Oct 2012
Accepted: 20 May 2013
Published online: 28 Feb 2014 *