arrow
Return

Speaker verification using speaker- and test-dependent fast score normalization

delete2007-01-01
delete27
delete
OA
AI
D
Daniel Ramos-Castro *
J
Julián Fiérrez
J
Joaquín González-Rodríguez
J
Javier Ortega-García
DOI:10.1016/j.patrec.2006.06.008delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
A novel score normalization scheme for speaker verification is presented. The proposed technique is based on the widely used test-normalization method (Tnorm), which compensates test-dependent variability using a fixed cohort of impostors. The new procedure selects a speaker-dependent subset of impostor models from the fixed cohort using a distance-based criterion. Selection of the sub-cohort is made using a distance measure based on a fast approximation of the Kullback-Leibler (KL) divergence for Gaussian mixture models (GMM). The proposed technique has been called KL-Tnorm, and outperforms Tnorm in computational efficiency. Experimental results using NIST 2005 Speaker Recognition Evaluation protocol also show a stable performance improvement of our method on standard speaker recognition systems. (c) 2006 Elsevier B.V. All rights reserved.
Keywords:
speaker verification
score normalization
Tnorm
Kullback-Leibler divergence
cohort selection
speaker-dependent
test-dependent
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

Pattern Recognition Letters cover
Pattern Recognition Letters
IF:
3.3
Papers:
7.8K
Citations:
1.6W

Organization

No organization information available