Experimental study on GMM-based speaker recognition

Wenxing Ye; Dapeng Wu; Antonio Nucci

doi:10.1117/12.849201

28 April 2010 Experimental study on GMM-based speaker recognition

Wenxing Ye, Dapeng Wu, Antonio Nucci

Proceedings Volume 7708, Mobile Multimedia/Image Processing, Security, and Applications 2010; 770804 (2010) https://doi.org/10.1117/12.849201
Event: SPIE Defense, Security, and Sensing, 2010, Orlando, Florida, United States

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.

Citation Download Citation

Wenxing Ye, Dapeng Wu, and Antonio Nucci "Experimental study on GMM-based speaker recognition", Proc. SPIE 7708, Mobile Multimedia/Image Processing, Security, and Applications 2010, 770804 (28 April 2010); https://doi.org/10.1117/12.849201

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available