Title :
Generalized Analysis in Sequence Kernel SVM
Author :
Jie, Li ; He-ping, Liu
Author_Institution :
Sch. of Inf. Eng., Univ. of Sci. & Technol. Beijing, Beijing, China
Abstract :
In the text-independent speaker recognition system, Support Vector Machine (SVM) equipped with sequence kernel has been widely used. In this paper, a generic structure conceiving sequence kernel has been encapsulated and in the structure we make an analytical comparison between two well used sequence kernel system-GMM Super vector Kernel (GSK) and Generalized Linear Discriminant Sequence (GLDS) showing how different attribute and levels of cues conveyed by speech utterances are being characterized within different sequence kernel. In the NIST 2006 SRE corpus, recognition rate improves significantly compared with the traditional GMM and Universal Background Models (GMM-UBM) system.
Keywords :
speaker recognition; support vector machines; text analysis; GLDS; GMM and universal background models; GMM super vector kernel; GMM-UBM; GSK; generalized analysis; generalized linear discriminant sequence; generic structure; kernel sequence; sequence kernel SVM; speech utterances; support vector machine; text-independent speaker recognition system; Cepstral analysis; Kernel; NIST; Speech; Support vector machine classification; Vectors; GMM Supervector Kernel; Generalized Linear Discriminant Sequence Kernel; sequence kernel; speaker recognition component;
Conference_Titel :
Computer Science & Service System (CSSS), 2012 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4673-0721-5
DOI :
10.1109/CSSS.2012.402
