首页 | 本学科首页   官方微博 | 高级检索  
     

考虑性别差异基于SVM的说话人识别研究
引用本文:张振领,贾仰理. 考虑性别差异基于SVM的说话人识别研究[J]. 计算机工程与设计, 2008, 29(6): 1516-1518
作者姓名:张振领  贾仰理
作者单位:聊城大学,计算机学院,山东,聊城,252059;北京航空航天大学,计算机学院,北京,100083
摘    要:说话人识别是目前身份认证及人工智能领域研究的一个热点,解决说话人识别问题具有重要的理论价值和深远的实用意义.基于语音鲜明个性特征和显著的性别差异,提出了一种考虑性别差异的说话人识别方法,并采用SVM分类器进行训练和测试.先对SVM分类器分别进行性别识别训练和同性集合内个体识别的分类训练,建立起相应的支持向量集合,以此为基础,先后进行说话人的性别识别测试和个体识别测试.实验结果表明,该方法可以有效提高闭集说话人识别系统的性能.

关 键 词:说话人识别  性别识别  支持向量机  机器学习  模式识别
文章编号:1000-7024(2008)06-1516-03
修稿时间:2007-06-08

Research of speaker recognition based on support vector machine with consideration of gender differences
ZHANG Zhen-ling,JIA Yang-li. Research of speaker recognition based on support vector machine with consideration of gender differences[J]. Computer Engineering and Design, 2008, 29(6): 1516-1518
Authors:ZHANG Zhen-ling  JIA Yang-li
Affiliation:ZHANG Zhen-ling1,JIA Yang-li2(1.School of Computer Science,Liaocheng University,Liaocheng 252059,China,2.School of Computer Science , Engineering,Beijing University of Aeronautics , Astronautics,Beijing 100083,China)
Abstract:At present,speaker recognition is a hotspot in authentication identification and artificial intelligence areas.There are important theoretic value and far-reaching practical meaning to resolve the question of speaker recognition.A speaker recognition method consider-ing gender differences is proposed in allusion to the individuation and remarkable gender differences of the voice of speakers,and SVM classifiers are applied to make training and testing.Firstly,SVM classifiers are trained for gender classifica...
Keywords:speaker recognition  gender recognition  support vector machine(SVM)  machine learning  pattern recognition  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号