A fast speaker verification with universal background support data selection

In this study, a fast universal background support imposter data selection method is proposed, which is integrated within a support vector machine (SVM) based speaker verification system. Selection of an informative background dataset is crucial in constructing a discriminative decision super-plane...

Full description

Saved in:
Bibliographic Details
Main Authors: Gang Liu, Jun-Won Suh, Hansen, J. H. L.
Format: Conference Proceeding
Language:English
Subjects:
adaptation
Adaptation models
Covariance matrix
Data models
Educational institutions
NIST
speaker verification
Support vector machines
SVM
Training
UBS
universal background dataset selection
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, a fast universal background support imposter data selection method is proposed, which is integrated within a support vector machine (SVM) based speaker verification system. Selection of an informative background dataset is crucial in constructing a discriminative decision super-plane between the enrollment and imposter speakers. Previous studies generally derive the optimal number of imposter examples from development data and apply to the evaluation data, which cannot guarantee consistent performance and often necessitate expensive searching. In the proposed method, the universal background dataset is derived so as to embed imposter knowledge in a more balanced way. Next, the derived dataset is taken as the imposter set in the SVM modeling process for each enrollment speaker. By using imposter adaptation, a more detailed subspace per target speaker can be constructed. Compared to the popular support-vector frequency based method, the proposed method can not only avoid parameter searching but offers a significant improvement and generalizes better on the unseen data.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2012.6288991