多类分类预选取的SVM在语音识别中的应用贺元元.pdfVIP

网络出版时间：2011-12-09 10:02 网络出版地址：/kcms/detail/11.2127.TP1002.065.html 2011-9-8 多类分类预选取的 SVM 在语音识别中的应用 1 1 2 贺元元 ，张雪英 ，刘晓峰 1 1 2 HE Yuanyuan ，ZHANG Xueying ，LIU Xiaofeng 1.太原理工大学信息工程学院，山西太原 030024 2.太原理工大学理学院数学系，山西太原 030024 1. College of Information Engineering, Taiyuan University of Technology, Taiyuan 030024, China 2. Dept. of Math, College of Science, Taiyuan University of Technology, Taiyuan 030024, China E-mail : tyzhangxy@163.co Multiclass Classification Pre-selection of SVM in Speech Recognition Application Abstract: For support vector machine training process, a lot of time is wasted in the complex calculations on non-support vectors. Especially for Large-scale speech recognition systems, training time of support vector machine on unnecessary overhead will be more remarkable. Kernel Fuzzy C-means clustering is a typical and dynamic clustering algorith , and the advantages of kernel is that it can non-linearly map the model space data to high dimensional feature space. This method is based on Kernel Fuzzy C-means clustering and combined the idea of one-versus-one method in ulticlass classification support vector achine. According to the established guidelines, it pre-selected the sample data which is likely to belong to the support vectors in training sample set, and the experiment has achieved satisfactory results in speech recognition application. By the method, the le