Speaker Recognition With Session Variability Normalization Based on MLLR Adaptation Transforms

We present a new modeling approach for speaker recognition that uses the maximum-likelihood linear regression (MLLR) adaptation transforms employed by a speech recognition system as features for support vector machine (SVM) speaker models. This approach is attractive because, unlike standard frame-b...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on audio, speech, and language processing Vol. 15; no. 7; pp. 1987 - 1998
Main Authors:	Stolcke, A., Kajarekar, S.S., Ferrer, L., Shrinberg, E.
Format:	Journal Article
Language:	English
Published:	IEEE 01-09-2007
Subjects:	Adaptation Cepstral analysis Feature extraction Intersession variability compensation Laboratories Linear regression Maximum likelihood linear regression maximum-likelihood linear regression-support vector machine (MLLR-SVM) Natural language processing NIST Recognition Regression Speaker recognition Speech Speech recognition Support vector machines Transforms
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	We present a new modeling approach for speaker recognition that uses the maximum-likelihood linear regression (MLLR) adaptation transforms employed by a speech recognition system as features for support vector machine (SVM) speaker models. This approach is attractive because, unlike standard frame-based cepstral speaker recognition models, it normalizes for the choice of spoken words in text-independent speaker verification without data fragmentation. We discuss the basics of the MLLR-SVM approach, and show how it can be enhanced by combining transforms relative to multiple reference models, with excellent results on recent English NIST evaluation sets. We then show how the approach can be applied even if no full word-level recognition system is available, which allows its use on non-English data even without matching speech recognizers. Finally, we examine how two recently proposed algorithms for intersession variability compensation perform in conjunction with MLLR-SVM.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Article-2 ObjectType-Feature-1
ISSN:	1558-7916 1558-7924
DOI:	10.1109/TASL.2007.902859