Integrated search technique for parameter determination of SVM for speech recognition

作     者：Teena Mittal R.K.Sharma 

作者机构：Department of Electronics and Communication Engineering Thapar University Department of Computer Science and Engineering Thapar University 

出 版 物：《Journal of Central South University》 (中南大学学报（英文版）)

年 卷 期：2016年第23卷第6期

页      面：1390-1398页

核心收录：

学科分类：0810[工学-信息与通信工程] 0711[理学-系统科学] 07[理学] 0806[工学-冶金工程] 0805[工学-材料科学与工程（可授工学、理学学位）] 0703[理学-化学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：support vector machine (SVM) predator prey optimization speech recognition Mel-frequency cepstral coefficients wavelet packets Hooke-Jeeves method 

摘      要：Support vector machine(SVM)has a good application prospect for speech recognition problems;still optimum parameter selection is a vital issue for *** improve the learning ability of SVM,a method for searching the optimal parameters based on integration of predator prey optimization(PPO)and Hooke-Jeeves method has been *** PPO technique,population consists of prey and predator *** prey particles search the optimum solution and predator always attacks the global best prey *** solution obtained by PPO is further improved by applying Hooke-Jeeves *** method is applied to recognize isolated words in a Hindi speech database and also to recognize words in a benchmark database TI-20 in clean and noisy environment.A recognition rate of 81.5%for Hindi database and 92.2%for TI-20 database has been achieved using proposed technique.