000083216 001__ 83216
000083216 005__ 20180317093240.0
000083216 02470 $$2DAR$$a10552
000083216 02470 $$2ISI$$a000246534800017
000083216 037__ $$aREP_WORK
000083216 245__ $$aA Kernel Trick For Sequences Applied to Text-Independent Speaker Verification Systems
000083216 269__ $$a2005
000083216 260__ $$bIDIAP$$c2005
000083216 336__ $$aReports
000083216 500__ $$aTo appear in In Pattern Recognition
000083216 520__ $$aThis paper present a principled SVM based speaker verification system. We propose a new framework and a new sequence kernel that can make use of any Mercer kernel at the frame level. An extension of the sequence kernel based on the Max operator is also proposed. The new system is compared to state-of-the-art GMM and other SVM based systems found in the literature on the Banca and Polyvar databases. The new system outperforms, most of the time, the other systems, statistically significantly. Finally, the new proposed framework clarifies previous SVM based systems and suggests interesting future research directions.
000083216 6531_ $$alearning
000083216 700__ $$aMariéthoz, Johnny
000083216 700__ $$0243961$$aBengio, Samy$$g140142
000083216 8564_ $$uhttp://publications.idiap.ch/downloads/reports/2005/mariethoz-idiap-rr-05-77.pdf$$zURL
000083216 8564_ $$s436362$$uhttps://infoscience.epfl.ch/record/83216/files/mariethoz-idiap-rr-05-77.pdf$$zn/a
000083216 909CO $$ooai:infoscience.tind.io:83216$$preport$$pSTI
000083216 909C0 $$0252189$$pLIDIAP$$xU10381
000083216 937__ $$aEPFL-REPORT-83216
000083216 970__ $$amariethoz:rr05-77/LIDIAP
000083216 973__ $$aEPFL$$sPUBLISHED
000083216 980__ $$aREPORT