Title :
A new Compact Support Kernel of support vector machines
Author :
Dong, Enqing ; Huang, Xiao
Author_Institution :
Sch. of Inf. Eng., Shandong Univ. at Weihai, Weihai
Abstract :
A new kernel based on the KCS (kernels with compact support) kernel family is proposed. The training time of the support vector machines of the new kernel is shorter than that of the common kernels. The support vector rate of the classifying machines also keeps in a low level. Compared with other classifying kernels, a great deal of experimental results indicates that the new kernel has a better classifying performance in VAD (voice active detection).
Keywords :
learning (artificial intelligence); pattern classification; support vector machines; VAD; kernel classification; kernel-compact support function; support vector machine training; voice active detection; Active noise reduction; Filters; Kernel; Machine learning; Signal to noise ratio; Support vector machine classification; Support vector machines; Testing; Working environment noise; Voice Active Detection; kernel functions; support vector machines;
Conference_Titel :
Communications, 2008. APCC 2008. 14th Asia-Pacific Conference on
Conference_Location :
Tokyo
Print_ISBN :
978-4-88552-232-1
Electronic_ISBN :
978-4-88552-231-4
