This paper presents an overview of a state-of-the-art text-independent speaker verification system. First, an introduction proposes a modular scheme of the training and test phases of a speaker verification system. Then, the most commonly speech parameterization used in speaker verification, namely, cepstral analysis, is detailed. Gaussian mixture modeling, which is the speaker modeling technique used in most systems, is then explained. A few speaker modeling alternatives, namely, neural networks and support vector machines, are mentioned. Normalization of scores is then explained, as this is a very important step to deal with real-world data. The evaluation of a speaker verification system is then detailed, and the detection error trade-off (DET) curve is explained. Several extensions of speaker verification are then enumerated, including speaker tracking and segmentation by speakers. Then, some applications of speaker verification are proposed, including on-site applications, remote applications, applications relative to structuring audio information, and games. Issues concerning the forensic area are then recalled, as we believe it is very important to inform people about the actual performance and limitations of speaker verification systems. This paper concludes by giving a few research trends in speaker verification for the next couple of years.
This article is part of the series Biometric Signal Processing.
A Tutorial on Text-Independent Speaker Verification
1 IRISA, INRIA & CNRS, Rennes Cedex 35042, France
2 LIA, University of Avignon, Avignon Cedex 9 84911, France
3 Laboratoire Dynamique du Langage, CNRS, Lyon Cedex 07 69369, France
4 ATVS, Universidad Politécnica de Madrid, Madrid 28040, Spain
5 DIVA Laboratory, Informatics Department, Fribourg University, Fribourg CH-1700, Switzerland
6 Lincoln Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02420-9108, USA
EURASIP Journal on Advances in Signal Processing 2004, 2004:101962 doi:10.1155/S1110865704310024
The electronic version of this article is the complete one and can be found online at: http://asp.eurasipjournals.com/content/2004/4/101962
|Received:||2 December 2002|
|Revisions received:||8 August 2003|
|Published:||21 April 2004|
© 2004 Bimbot et al.
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.