摘要
支持向量机(SVM)是在统计学习理论的基础上发展起来的一种新的通用学习方法。自动语种辨识是语音信号处理中新出现的分支,也是一项较难的课题。该文提出的模糊判决支持向量机(FDSVM)是对支持向量机的判决结果的合理化改进,并应用于自动语种辨识系统。利用OGI-TS电话语音库对新算法的性能进行测试,然后给出实验结果。结果表明,该算法相对于传统算法是一种更有效的方法。
A support vector machines(SVM)is a new powerful classification machines from the theory of learning systems.Automatic language identification is a new and difficult embranchment of the speech signal processing.In this paper,Fussy Discrimination SVM(FDSVM)algorithm is provided which is an improving method based on SVM.Some experiments are conducted using OGI-TS telephone speech corpus.Then experiments results are described.It is shown that FDSVM is another more efficient method comparing with traditional ways.
出处
《计算机工程与应用》
CSCD
北大核心
2004年第21期69-71,共3页
Computer Engineering and Applications
基金
国家部委基金项目(编号:514950307)资助
关键词
模糊判决支持向量机
语种辨识
线性预测倒谱系数
Fussy Discrimination Support Vector Machines(FDSVM),Language Identification(LI ),Linear Prediction Cepstrum Coefficients(LPCC)