Speaker verification using Adapted Gaussian mixture models

Speaker verification using Adapted Gaussian mixture models (2000)

Cached

Download Links

[www.cse.ohio-state.edu]

by Douglas A. Reynolds , Thomas F. Quatieri , Robert B. Dunn

Venue:	Digital Signal Processing
Citations:	385 - 15 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Speaker verification using Adapted Gaussian mixture models	INFERENCE
AUTHOR NAME	Douglas A. Reynolds	SVM HeaderParse 0.2
AUTHOR AFFIL	M.I.T. Lincoln Laboratory, 244 Wood St., Lexington	SVM HeaderParse 0.2
AUTHOR ADDR	Massachusetts 02420	SVM HeaderParse 0.2
AUTHOR NAME	Thomas F. Quatieri	SVM HeaderParse 0.2
AUTHOR AFFIL	M.I.T. Lincoln Laboratory, 244 Wood St., Lexington	SVM HeaderParse 0.2
AUTHOR ADDR	Massachusetts 02420	SVM HeaderParse 0.2
AUTHOR NAME	Robert B. Dunn	SVM HeaderParse 0.2
AUTHOR AFFIL	M.I.T. Lincoln Laboratory, 244 Wood St., Lexington	SVM HeaderParse 0.2
AUTHOR ADDR	Massachusetts 02420	SVM HeaderParse 0.2
ABSTRACT	In this paper we describe the major elements of MIT Lincoln Laboratory’s Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance is also described and discussed. Finally, representative performance benchmarks and system behavior experiments on NIST SRE corpora are presented. © 2000 Academic Press Key Words: speaker recognition; Gaussian mixture models; likelihood ratio detector; universal background model; handset normalization; NIST evaluation. 1.	SVM HeaderParse 0.2
YEAR	2000	INFERENCE
VENUE	Digital Signal Processing	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	2000	INFERENCE
VOLUME	10	INFERENCE
CITATIONS	34 found	ParsCit 1.0