EXPLORING KERNELS IN SVM-BASED CLASSIFICATION OF LARYNX PATHOLOGY FROM HUMAN VOICE

被引：0
|
作者：
Vaiciukynas, Evaldas [1 ]
Gelzinis, Adas [1 ]
Bacauskiene, Marija [1 ]
Verikas, Antanas [1 ]
Vegiene, Aurelija [1 ]
机构：
[1] Kaunas Univ Technol, Dept Elect & Control Instrumentat, Kaunas, Lithuania
来源：
ELECTRICAL AND CONTROL TECHNOLOGIES | 2010年
关键词：
Laryngeal disorder; Pathological voice; Voice processing; Mel-frequency cepstral coefficients; Sequence kernel; Principal canonical correlation; Monte-Carlo sampling; Kullback-Leibler divergence; Earth mover's distance; GMM; SVM;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper identification of laryngeal disorders using cepstral parameters of human voice is investigated. Mel-frequency cepstral coefficients (MFCC), extracted from audio recordings, are further approximated, using 3 strategies: sampling, averaging, and estimation. SVM and LS-SVM categorize preprocessed data into normal, nodular, and diffuse classes. Since it is a three-class problem, various combination schemes are explored. Constructed custom kernels outperformed a popular non-linear RBF kernel. Features, estimated with GMM, and SVM kernels, designed to exploit this information, is an interesting fusion of probabilistic and discriminative models for human voice-based classification of larynx pathology.
引用
收藏
页码：67 / +
页数：2
相关论文
共 50 条
  • [1] Exploring similarity-based classification of larynx disorders from human voice
    Vaiciukynas, Evaldas
    Verikas, Antanas
    Gelzinis, Adas
    Bacauskiene, Marija
    Uloza, Virgilijus
    [J]. SPEECH COMMUNICATION, 2012, 54 (05) : 601 - 610
  • [2] SVM-Based Classification of Moving Objects
    Li, Zhanchuang
    Jiang, Jianmin
    Xiao, Guoqiang
    [J]. MULTIMEDIA, COMPUTER GRAPHICS AND BROADCASTING, PROCEEDINGS, 2009, 60 : 37 - 45
  • [3] SVM-based audio scene classification
    Jiang, HC
    Bai, JM
    Zhang, SW
    Xu, B
    [J]. PROCEEDINGS OF THE 2005 IEEE INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING AND KNOWLEDGE ENGINEERING (IEEE NLP-KE'05), 2005, : 131 - 136
  • [4] Research of SVM-based document classification
    Zhang, ZhenNan
    Xu, Qian
    Cui, Junbo
    Pu, Duan
    [J]. Information, Management and Algorithms, Vol II, 2007, : 260 - 263
  • [5] An Ensemble SVM-based Approach for Voice Activity Detection
    Dey, Jayanta
    Bin Hossain, Md Sanzid
    Haque, Mohammad Ariful
    [J]. 2018 10TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (ICECE), 2018, : 297 - 300
  • [6] Kernels evaluation of SVM-based estimators for inverse scattering problems
    Bermani, E.
    Boni, A.
    Kerhet, A.
    Massa, A.
    [J]. PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER, 2005, 53 : 167 - 188
  • [7] An optimal svm-based text classification algorithm
    Wang, Zi-Qiang
    Sun, Xia
    Zhang, De-Xian
    Li, Xin
    [J]. PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2006, : 1378 - +
  • [8] SVM-based video scene classification and segmentation
    Zhu, Yingying
    Ming, Zhong
    [J]. MUE: 2008 INTERNATIONAL CONFERENCE ON MULTIMEDIA AND UBIQUITOUS ENGINEERING, PROCEEDINGS, 2008, : 407 - 412
  • [9] Multiresolution histograms for SVM-based texture classification
    Andra, S
    Wu, YJ
    [J]. IMAGE ANALYSIS AND RECOGNITION, 2005, 3656 : 754 - 761
  • [10] SVM-based classification method for poetry style
    He, Zhong-Shi
    Liang, Wen-Ting
    Li, Liang-Yan
    Tian, Yu-Fang
    [J]. PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2007, : 2936 - +
12345