A GMM SUPERVECTOR KERNEL WITH THE BHATTACHARYYA DISTANCE FOR SVM BASED SPEAKER RECOGNITION

被引：0
|
作者：
You, Chang Huai [1 ]
Lee, Kong Aik [1 ]
Li, Haizhou [1 ]
机构：
[1] ASTAR, Inst Infocomm Res I2R, Singapore, Singapore
来源：
2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS | 2009年
关键词：
Gaussian Mixture Model; Support Vector Machine; Supervector; Speaker Verification; NIST Evaluation; VERIFICATION;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
Gaussian mixture model (GMM) supervector is one of the effective techniques in text independent speaker recognition. In our previous work, we introduce the GMM-UBM mean interval (GUMI) concept based on the Bhattacharyya distance. Subsequently GUMI kernel was successfully used in conjunction with support vector machine (SVM) for speaker recognition. Besides the first order statistics, it is generally believed that speaker cues are also partly conveyed by second order statistics. In this paper, we extend the Bhattacharyya-based SVM kernel by constructing the supervector with the mean statistical vector and the covariance statistical vector. Comparing with the Kullback-Leibler (KL) kernel, we demonstrate the effectiveness of the new kernel on the 2006 National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) dataset.
引用
收藏
页码：4221 / 4224
页数：4
相关论文
共 50 条
  • [1] An SVM Kernel With GMM-Supervector Based on the Bhattacharyya Distance for Speaker Recognition
    You, Chang Huai
    Lee, Kong Aik
    Li, Haizhou
    IEEE SIGNAL PROCESSING LETTERS, 2009, 16 (1-3) : 49 - 52
  • [2] GMM-SVM Kernel With a Bhattacharyya-Based Distance for Speaker Recognition
    You, Chang Huai
    Lee, Kong Aik
    Li, Haizhou
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2010, 18 (06): : 1300 - 1312
  • [3] Speaker Verification Using SVM Kernel with GMM-Supervector Based on the Mahalanobis Distance
    Kim, Hyoung-Gook
    Shin, Dong
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2010, 29 (03): : 216 - 221
  • [4] SVM based speaker verification using a GMM supervector kernel and nap variability compensation
    Campbell, W. M.
    Sturim, D. E.
    Reynolds, D. A.
    Solomonoff, A.
    2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, : 97 - 100
  • [5] Dialect Recognition Using a Phone-GMM-Supervector-Based SVM Kernel
    Biadsy, Fadi
    Hirschberg, Julia
    Collins, Michael
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 753 - +
  • [6] GMM-based Bhattacharyya kernel Fisher Discriminant Analysis for speaker recognition
    Chao, YH
    Wang, HM
    Chang, RC
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 649 - 652
  • [7] SVM based speaker selection using GMM supervector for rapid speaker adaptation
    Wang, Jian
    Lei, Jianjun
    Guo, Jun
    Yang, Zhen
    SIMULATED EVOLUTION AND LEARNING, PROCEEDINGS, 2006, 4247 : 617 - 624
  • [8] Audio-based Emotion Recognition using GMM Supervector an SVM Linear Kernel
    Dinh-Son Tran
    Yang, Hyung-Jeong
    Kim, Soo-Hyung
    Lee, Guee Sang
    Luu-Ngoc Do
    Ngoc-Huynh Ho
    Van Quan Nguyen
    2ND INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND SOFT COMPUTING (ICMLSC 2018), 2015, : 169 - 173
  • [9] EMOTIONAL SPEECH RECOGNITION BASED ON SVM WITH GMM SUPERVECTOR
    Chen Yanxiang Xie Jian (Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine
    Journal of Electronics(China), 2012, (Z2) : 339 - 344
  • [10] EMOTIONAL SPEECH RECOGNITION BASED ON SVM WITH GMM SUPERVECTOR
    Chen Yanxiang Xie Jian Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science Information Hefei University of Technology Hefei China
    JournalofElectronics(China), 2012, 29(Z2) (China) : 339 - 344
12345