摘要
在分析说话人识别原理的基础上，分别从说话人识别的特征提取、说话人模型等方面进行了综述，并讨论了说话人识别的优点和不足，展望了其应用研究的前景。
The paper reviews the principles of the speaker recognition, and then reviews the feature extraction methods, speaker models based on the speaker recognition . In the conclusion section, it discusses the advantages and shortcomings of speaker recognition and looks forward to its attractive application research prospect.
作者
刘雪燕
张娜
袁宝玲
LIU Xue-yan, ZHANG Na ,YUAN Bao-ling （1. Department of Information Engineering, Zhongshan Torch Polytechnic, Zhongshan 528436, China; 2. Army 68026, Team 57, Lanzhou 730050, China）
出处
《电脑知识与技术》
2009年第1期169-171,共3页
Computer Knowledge and Technology
基金
中山火炬职业技术学院校级基金（2007Y11）
关键词
说话人识别
特征提取
说话人模型
speaker recognition
feature extraction
speaker model
