Using Pseudo-Key for Language Recognition System Design

Abstract

In this paper, we present a novel pseudo-key analysis approach for the fusion system of language recognition. The state-of-the-art language recognition systems for the NIST language recognition evaluation (LRE) commonly consist of multiple language classifiers. To avoid the fusion system to be spoiled by one abnormal classifier, pseudo keys are designed to check the integrity of each of the individual classifiers before the system fusion. The scores of individual classifiers are cross-validated based the pseudo keys. The language recognition experiments are conducted on the 2007 NIST LRE corpus based on the Institute for Infocomm Research's submission.