%0 Journal Article
%T Effects Of Background Data Duration On Speaker Verification Performance
%A Cemal HAN£¿L£¿£¿
%A Figen ERTA£¿
%J Uluda£¿ University Journal of The Faculty of Engineering and Architecture
%D 2013
%I Uludag University
%X Gaussian mixture models with universal background model (GMM-UBM) and vector quantization with universal background model (VQ-UBM) are the two well-known classifiers used for speaker verification. Generally, UBM is trained with many hours of speech from a large pool of different speakers. In this study, we analyze the effect of data duration used to train UBM on text-independent speaker verification performance using GMM-UBM and VQ-UBM modeling techniques. Experiments carried out NIST 2002 speaker recognition evaluation (SRE) corpus show that background data duration to train UBM has small impact on recognition performance for GMM-UBM and VQ-UBM classifiers.
%K Speaker verification
%K Gaussian mixture model
%K Vector Quantization
%K Universal background model
%U http://mmfdergi.uludag.edu.tr/Dergi/cilt18sayi1/mak18_01-11(syf111-119).pdf