A Parameters Optimization Method of v-Support Vector Machine and Its Application in Speech Recognition

Abstract

An important factor that influences the performance of support vector machine is how to select its parameters. In traditional C-support vector machine, it is difficult to select penalty parameter C and kernel parameters, inappropriate choice of those values may cause deterioration of its performance and increase algorithm complexity. In order to solve those problems, in this paper, selected v - support vector machine as the research object, proposed an optimal parameters search method for the Gaussian kernel v - support vector machine based on improved particle swarm optimization, constructed a non- specific person and isolated words speech recognition system based on v - support vector machine using the optimized parameters firstly. Experiments show that this new v - support vector machine method achieves better speech recognition correct rates than traditional C-support vector machine in different signal to noise ratios and different words, this new improved method of optimizing v - SVM parameters is very efficient and has shorter convergence time, and makes v - support vector machine have better Performance in speech recognition system.