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.

/pdf/a-tutorial-on-text-independent-speaker-verification-43syqe9ebt.pdf

A tutorial on text-independent speaker verification

http://ccc.inaoep.mx/~villasen/bib/SVM%20for%20Language%20and%20speaker%20recognition.pdf

Support vector machines for speaker and language recognition

The National Institute of Standards and Technology (NIST) has coordinated annual scientific evaluations of text-independent speaker recognition since 1996. These evaluations aim to provide important contributions to the direction of research efforts and the calibration of technical capabilities. They are intended to be of interest to all researchers working on the general problem of text-independent speaker recognition. To this end, the evaluations are designed to be simple, fully supported, accessible and focused on core technology issues. The evaluations have focused primarily on speaker detection in the context of conversational telephone speech. More recent evaluations have also included related tasks, such as speaker segmentation, and have used data in addition to conversational telephone speech. The evaluations are designed to foster research progress, with the objectives of:

The NIST speaker recognition evaluation program

This paper presents a text-independent speaker verification system using support vector machines (SVMs) with score-space kernels. Score-space kernels generalize Fisher kernels and are based on underlying generative models such as Gaussian mixture models (GMMs). This approach provides direct discrimination between whole sequences, in contrast with the frame-level approaches at the heart of most current systems. The resultant SVMs have a very high dimensionality since it is related to the number of parameters in the underlying generative model. To address problems that arise in the resultant optimization we introduce a technique called spherical normalization that preconditions the Hessian matrix. We have performed speaker verification experiments using the PolyVar database. The SVM system presented here reduces the relative error rates by 34% compared to a GMM likelihood ratio system.

/pdf/speaker-verification-using-sequence-discriminant-support-4kamgjd9cv.pdf

Speaker verification using sequence discriminant support vector machines

This paper presents the ALIZE free speaker recognition toolkit. ALIZE is designed and developed within the framework of the ALIZE project, a part of the French Research Ministry Technolangue program. The paper focuses on the innovative aspects of ALIZE and illustrates them by some examples. An experimental validation of the toolkit during the NIST 2004 speaker recognition evaluation campaign is also proposed.

ALIZE, a free toolkit for speaker recognition

Current best performing speaker recognition algorithms are based on Gaussian Mixture Models (GMM). Their results are not satisfactory for all experimental conditions, especially for the mismatched (train/test) conditions. Support Vector Machine is a new and very promissing technique in statistical learning theory. Recently, this technique produced very interesting results in image processing [2], [3], [4] and for the fusion of experts in biometric authentification [5]. In this paper we address the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.

Combining GMM's with Suport Vector Machines for Text-independent Speaker Verification

This article presents the text-independent speaker detection and tracking systems developed by the members of the {ELISA} Consortium for the {NIST'99} speaker recognition evaluation campaign. {ELISA} is a consortium grouping researchers of several laboratories sharing software modules, resources and experimental protocols. Each system is briefly described, and comparative results on the {NIST'99} evaluation tasks are discussed

The ELISA Systems for the NIST"99 Evaluation in Speaker Detection and Tracking

This paper presents a general overview of the current research activities in the European PICASSO project on speaker verification for telephone applications. First, the general formalism used by the project is described. Then the scientific issues under focus are discussed in detail. Finally, the paper briefly describes the Picassoft research platform. Along the article, entry points to more specific work also published in the Eurospeech99 proceedings are given.

An overview of the Picasso project research activities in speaker verification for telephone applications

On the Use of Prior Knowledge in Normalization Schemes for Speaker Verification

In this article we address the issue of using the Support Vector Learning technique in combination with the currently well performing Gaussian Mixture Models (GMM) for speaker verification experiments. Support Vector Machines (SVM) is a new and very promising technique in statistical learning theory. Recently this technique produced very interesting results in image processing [1] [2] [3], and for the fusion of the experts in biometric authentication [4]. The SVM were already applied for speaker identification purpose, in [5] and [6]. In these applications, the frames computed on the speakers’ speech signal are given as input vectors to train the speaker specific SVM’s. In this work, we propose a new feature representation based on GMM to construct the input vectors to train the SVM to discriminate the true-target speaker access class from the non-target speaker access class. The results obtained with this hybrid GMM-SVM technique are compared to the classical Log-Likelihood Ratio (LLR) technique, on a sub-set of NIST’99 evaluation data which is a part of the Switchboard corpus. The influence of the hnorm normalization is also studied. In all the cases, the proposed systems using SVM outperform the classical LLR based systems.

Jamal Kharroubi

Papers

Combining GMM's with Suport Vector Machines for Text-independent Speaker Verification

The ELISA Systems for the NIST"99 Evaluation in Speaker Detection and Tracking

An overview of the Picasso project research activities in speaker verification for telephone applications

On the Use of Prior Knowledge in Normalization Schemes for Speaker Verification

Text-independent speaker verification using support vector machines.