An evaluation of one-class classification techniques for speaker verification

9Citations
Citations of this article
19Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Speaker verification is a challenging problem in speaker recognition where the objective is to determine whether a segment of speech in fact comes from a specific individual. In supervised machine learning terms this is a challenging problem as, while examples belonging to the target class are easy to gather, the set of counter-examples is completely open. This makes it difficult to cast this as a supervised classification problem as it is difficult to construct a representative set of counter examples. So we cast this as a one-class classification problem and evaluate a variety of state-of-the-art one-class classification techniques on a benchmark speech recognition dataset. We construct this as a two-level classification process whereby, at the lower level, speech segments of 20 ms in length are classified and then a decision on an complete speech sample is made by aggregating these component classifications. We show that of the one-class classification techniques we evaluate, Gaussian Mixture Models shows the best performance on this task. © 2008 Springer Science+Business Media B.V.

Cite

CITATION STYLE

APA

Brew, A., Grimaldi, M., & Cunningham, P. (2007). An evaluation of one-class classification techniques for speaker verification. Artificial Intelligence Review, 27(4 SPEC. ISS.), 295–307. https://doi.org/10.1007/s10462-008-9071-8

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free