Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration...

Full description

Saved in:
Bibliographic Details
Main Authors: McLaren, Mitchell, Baker, Brendan, Vogt, Robbie, Sridharan, Sridha
Format: Conference Proceeding
Language:English
Subjects:
Australia
data selection
Extraterrestrial measurements
Frequency measurement
impostors
Kernel
Laboratories
Robustness
Speaker recognition
Speech
support vector machine
Support vector machine classification
Support vector machines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2010.5495620