This paper presents meta-learning schemes aimed at improving fusion of low and high level information for speaker verification in clean and noisy environments. While traditional systems fuse several classifier outputs in a uniform fashion independently of test quality, the proposed schemes use selective fusion weights according to test quality. A decrease of more than 20% under noisy conditions and 10% under clean conditions could be obtained with little calibration.
Cite as: Solewicz, Y.A., Koppel, M. (2004) Enhanced fusion methods for speaker verification. Proc. 9th Conference on Speech and Computer (SPECOM 2004), 388-392
@inproceedings{solewicz04_specom,
author={Yosef A. Solewicz and Moshe Koppel},
title={{Enhanced fusion methods for speaker verification}},
year=2004,
booktitle={Proc. 9th Conference on Speech and Computer (SPECOM 2004)},
pages={388--392}
}