改进PSO-SVM在说话人识别中的应用  

Application of Improved PSO-SVM Approach in Speaker Recognition

作　　者：李明[1] 张勇[1] 李军权[1] 张亚芬[1] 

机构地区：[1]兰州理工大学计算机与通信学院,兰州730050

出　　处：《电子科技大学学报》2007年第6期1345-1349,共5页Journal of University of Electronic Science and Technology of China

基　　金：甘肃省教育厅科研项目(0603-10)

摘　　要：为了加快粒子群优化算法的收敛速度,增强全局的搜索能力,通过对粒子群优化算法中惯性权重和全局最优值的分析,提出了一种根据迭代次数而自适应变化的惯性权重的粒子群优化方法。改进后的粒子群算法在防止陷入局部最优的能力方面有了明显的增强,同时,给出了应用粒子群优化算法训练支持向量机的方法,并将其应用于说话人识别。实验结果证实了在说话人识别中改进PSO-SVM方法比其他传统方法能获得更好的识别精度和识别速度。In order to increase the convergent speed and to improve the overall searching ability of the algorithm, a Particle Swarm Optimization （PSO） method is proposed with adaptive inertia weight by the change of the number of iterations based on the analysis of inertia weight global best fitness of the PSO. The improved PSO increases the ability to avoid local optimum. Then a speaker recognition method using this improved algorithm to train Support Vector Machine （SVM） is presented. The experimental results show that the presented SVM method optimized by PSO for speaker recognition can achieve higher recognition accuracy and higher recognition speed.

关 键 词：惯性权重 粒子群优化算法 说话人识别 支持向量机 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]