Skip to main navigation Skip to search Skip to main content

Experimental study on GMM-based speaker recognition

Wenxing Ye, Dapeng Wu, Antonio Nucci

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

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. © 2010 Copyright SPIE - The International Society for Optical Engineering.
Original languageEnglish
Title of host publicationMobile Multimedia/Image Processing, Security, and Applications 2010
Volume7708
DOIs
Publication statusPublished - 2010
Externally publishedYes
EventMobile Multimedia/Image Processing, Security, and Applications 2010 - Orlando, FL, United States
Duration: 5 Apr 20106 Apr 2010

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7708
ISSN (Print)0277-786X

Conference

ConferenceMobile Multimedia/Image Processing, Security, and Applications 2010
PlaceUnited States
CityOrlando, FL
Period5/04/106/04/10

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

  • GMM
  • MFCC
  • Speaker recognition

Fingerprint

Dive into the research topics of 'Experimental study on GMM-based speaker recognition'. Together they form a unique fingerprint.

Cite this