Paper Info
Title
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.
Year
DOI
Venue
2008
10.1109/CHINSL.2008.ECP.55
ISCSLP
Keywords
Field
DocType
multiple language classifiers,speech recognition,pseudo-key,nist language recognition evaluation,natural language processing,spoken language recognition,language recognition system design,system design,acoustics,support vector machines,speech,nist,cross validation
Pattern recognition,Computer science,Support vector machine,Systems design,Speech recognition,NIST,Language recognition,Artificial intelligence,Natural language processing,Classifier (linguistics),Fusion system,Support vector machine classification
Conference
ISBN
Citations 
PageRank 
978-1-4244-2943-1
0
0.34
References 
Authors
5
3
Name
Order
Citations
PageRank
Hanwu Sun19814.15
Bin Ma260047.26
Haizhou Li33678334.61