Share Email Print

Proceedings Paper

Experimental study on GMM-based speaker recognition
Author(s): Wenxing Ye; Dapeng Wu; Antonio Nucci
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Speaker recognition plays a very important role in the field of biometric security. In order to improve the recognition performance, many pattern recognition techniques have be explored in the literature. Among these techniques, the Gaussian Mixture Model (GMM) is proved to be an effective statistic model for speaker recognition and is used in most state-of-the-art speaker recognition systems. The GMM is used to represent the 'voice print' of a speaker through modeling the spectral characteristic of speech signals of the speaker. In this paper, we implement a speaker recognition system, which consists of preprocessing, Mel-Frequency Cepstrum Coefficients (MFCCs) based feature extraction, and GMM based classification. We test our system with TIDIGITS data set (325 speakers) and our own recordings of more than 200 speakers; our system achieves 100% correct recognition rate. Moreover, we also test our system under the scenario that training samples are from one language but test samples are from a different language; our system also achieves 100% correct recognition rate, which indicates that our system is language independent.

Paper Details

Date Published: 28 April 2010
PDF: 9 pages
Proc. SPIE 7708, Mobile Multimedia/Image Processing, Security, and Applications 2010, 770804 (28 April 2010); doi: 10.1117/12.849201
Show Author Affiliations
Wenxing Ye, Univ. of Florida (United States)
Dapeng Wu, Univ. of Florida (United States)
Antonio Nucci, Narus Inc. (United States)

Published in SPIE Proceedings Vol. 7708:
Mobile Multimedia/Image Processing, Security, and Applications 2010
Sos S. Agaian; Sabah A. Jassim, Editor(s)

© SPIE. Terms of Use
Back to Top