Support Vector Domain Description for speaker recognition

被引：4
|
作者：
Xin, D [1 ]
Wu, ZH [1 ]
Zhang, WF [1 ]
机构：
[1] Zhejiang Univ, Dept Comp Sci & Engn, Hangzhou 310027, Peoples R China
来源：
NEURAL NETWORKS FOR SIGNAL PROCESSING XI | 2001年
关键词：
D O I：
10.1109/NNSP.2001.943152
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A novel approach to speaker recognition is presented. The method, called Support Vector Data Description (SVDD), was originally suggested by Vapnik, interpreted as a novelty detectors by Tax and Duin. In this paper, we use this data domain description as a classifier. It contains support vectors describing the sphere separating the samples. With a minimal radius R, this classifier achieve good performance in finding abnormal samples within the open set test. We use it in the speaker identification application. And the result on YOHO database are presented.
引用
收藏
页码：481 / 488
页数：8
相关论文
共 50 条
  • [1] Support vector domain description
    Tax, DMJ
    Duin, RPW
    [J]. PATTERN RECOGNITION LETTERS, 1999, 20 (11-13) : 1191 - 1199
  • [2] Phonetic speaker recognition with support vector machines
    Campbell, WM
    Campbell, JP
    Reynolds, DA
    Jones, DA
    Leek, TR
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16, 2004, 16 : 1377 - 1384
  • [3] Support vector machines for speaker and language recognition
    Campbell, WM
    Campbell, JP
    Reynolds, DA
    Singer, E
    Torres-Carrasquillo, PA
    [J]. COMPUTER SPEECH AND LANGUAGE, 2006, 20 (2-3): : 210 - 229
  • [4] Confidence support vector domain description
    Liu Sanyang~1
    2.School of Computer Science and Technology
    [J]. Journal of Systems Engineering and Electronics, 2009, 20 (04) : 852 - 857
  • [5] Confidence support vector domain description
    Liu Sanyang
    Liang Jinjin
    Wu De
    Duan Wei
    [J]. JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS, 2009, 20 (04) : 852 - 857
  • [6] On the regularization path of the support vector domain description
    Hansen, Michael Sass
    Sjostrand, Karl
    Larsen, Rasmus
    [J]. PATTERN RECOGNITION LETTERS, 2010, 31 (13) : 1919 - 1923
  • [7] Position regularized Support Vector Domain Description
    Wang, Chang-Dong
    Lai, JianHuang
    [J]. PATTERN RECOGNITION, 2013, 46 (03) : 875 - 884
  • [8] Smoothly approximated support vector domain description
    Zheng, Songfeng
    [J]. PATTERN RECOGNITION, 2016, 49 : 55 - 64
  • [9] Speaker recognition using continuous density support vector machines
    Xin, D
    Wu, ZH
    [J]. ELECTRONICS LETTERS, 2001, 37 (17) : 1099 - 1101
  • [10] The entire regularization path for the support vector domain description
    Sjostrand, Karl
    Larsen, Rasmus
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2006, PT 1, 2006, 4190 : 241 - 248
12345