Confidence based multiple classifier fusion in speaker verification
Huenupan_Fernando.pdf (751.8Kb)Abstract
A novel framework that applies Bayes-based confidence measure for multiple classifier system fusion is proposed. Compared with ordinary Bayesian fusion, the presented approach can lead to reductions as high as 37% and 35% in EER and ROC curve area, respectively, in speaker verification.
Identifier
URI: https://repositorio.uchile.cl/handle/2250/125240
DOI: 10.1016/j.patrec.2008.01.015
ISSN: 0167-8655
Quote Item
PATTERN RECOGNITION LETTERS Volume: 29 Issue: 7 Pages: 957-966 Published: MAY 1 2008
Collections