Emotional speaker verification with linear adaptation

Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable per...

Full description

Saved in:
Bibliographic Details
Main Authors: Fanhu Bie, Dong Wang, Zheng, Thomas Fang, Ruxin Chen
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Adaptation models
emotional speech
Hidden Markov models
MLLR
speaker verification
Speech
Training
Transforms
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable performance improvement, particularly with CMLLR (about 10% relative EER reduction in average). We also find that the performance gain can be significantly increased with a large set of training data for the transform estimation.
DOI:10.1109/ChinaSIP.2013.6625304