The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 89-293
Full Name: Balwant A. Sonkamble
Position: Assistant Professor
Age: ON
Sex: Male
Address: F. No. 4, Pooja Apartment, S. No.73/14,Dattangar Road,Katraj,Pune,Maharashtra state, India-411046
Country: INDIA
Tel: 02024366692
Tel prefix:
Fax:
E-mail address: sonbalwant@yahoo.com
Other E-mails:
Title of the Paper: Improving Speech Recognition Performance using Support Vector Machines
Authors as they appear in the Paper: Mr. Balwant A. Sonkamble, Dr. D. D. Doye, Mrs. Sulochana Sonkamble
Email addresses of all the authors:
Number of paper pages: 10
Abstract: The use of different kernel functions plays very important role for improving performance while developing pattern classification systems. In this paper, we have selected speech recognition problem as a pattern classification problem. The use of linear kernel function, polynomial kernel function and sigmoid kernel function considered for comparing the improvements in our experimental study. The RBF kernel function gives very efficient performance as compared to other kernel functions. We have used One-versus-One approach, which the popular and efficient approach for constructing SVM Classifiers with voting algorithm.
Keywords: Support Vector Machines, Kernel Function, Separating Hyperplane, Structural Risk Minimization, One-versus-One Approach, One-versus-All approach.
EXTENSION of the file: .pdf
Special (Invited) Session: An Efficient use of Support Vector Machines for Speech Signal Classification
Organizer of the Session: 697-343
How Did you learn about congress:
IP ADDRESS: 124.247.239.68
