Compensation of channel effects for support vector machines based speaker verification

Cemal Hanilçi, Figen Ertaş · 2012

In this paper, we analyze the effect of channel compensation technique on support vector machines (SVM) based speaker verification performance and compare with another well-known speaker modeling algorithm Gaussian Mixture Models with universal background model (GMM-UBM). Experiments conducted on NIST 2002 SRE shows that channel compensation considerable improves the speaker verification accuracy.

Read the paper · More papers on PaperTik