Speaker recognition using matched filters

Nowadays state-of-the-art speaker recognition systems obtain quite accurate results for both text-independent and text-dependent tasks as long as they are trained on a fair amount of development data from the target domain, and as long as the target data is clean. In this work we investigate the use...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5555 - 5559
Main Author Aronowitz, Hagai
Format Conference Proceeding Journal Article
LanguageEnglish
Published IEEE 01.03.2016
Subjects
Conferences
Covariance matrices
domain adaptation
Electronics
Estimation
Feature extraction
i-vector centering
matched filter
Matched filters
NIST
score normalization
Signal to noise ratio
Speaker recognition
speaker verification
Speech
Speech recognition
Stabilization
Tasks
Online AccessGet full text

Cover

More Information
Summary:Nowadays state-of-the-art speaker recognition systems obtain quite accurate results for both text-independent and text-dependent tasks as long as they are trained on a fair amount of development data from the target domain, and as long as the target data is clean. In this work we investigate the use of matched filters for speaker recognition in the framework of a small in-domain development data. We show how a matched filter can be optimized to maximize SNR (signal to noise ratio) when the noise component includes both intra-speaker variability and center/mean hyper-parameter variability. The proposed method generalizes our previous method named score stabilization and obtains significant speaker recognition error reductions.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:2379-190X
DOI:10.1109/ICASSP.2016.7472740