SVM speaker verification using session variability modelling and GMM supervectors

被引：0
|
作者：
McLaren, M. [1 ]
Vogt, R. [1 ]
Sridharan, S. [1 ]
机构：
[1] Queensland Univ Technol, Speech & Aud Res Lab, Brisbane, Qld, Australia
来源：
ADVANCES IN BIOMETRICS, PROCEEDINGS | 2007年 / 4642卷
基金：
澳大利亚研究理事会;
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper demonstrates that modelling session variability during GMM training can improve the performance of a GMM supervector SVM speaker verification system. Recently, a method of modelling session variability in GMM-UBM systems has led to significant improvements when the training and testing conditions are subject to session effects. In this work, session variability modelling is applied during the extraction of GMM supervectors prior to SVM speaker model training and classification. Experiments performed on the NIST 2005 corpus show major improvements over the baseline GMM supervector SVM system.
引用
收藏
页码：1077 / +
页数：2
相关论文
共 50 条
  • [11] Determination of a speaker's age and gender with an SVM classifier based on GMM supervectors
    Yucesoy, Ergun
    Nabiyev, Vasif V.
    [J]. JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, 2016, 31 (03): : 501 - 510
  • [12] A new hybrid GMM/SVM for speaker verification
    Liu, Minghui
    Xie, Yanlu
    Yao, Zhiqiang
    Dai, Beiqian
    [J]. 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, PROCEEDINGS, 2006, : 314 - +
  • [13] A Robust SVM/GMM Classifier for Speaker Verification
    Cirovic, Zoran
    Cirovic, Natasa
    [J]. SPEECH AND COMPUTER, 2014, 8773 : 74 - 80
  • [14] Video-Based Face Verification with Local Binary Patterns and SVM Using GMM Supervectors
    Pereira, Tiago F.
    Angeloni, Marcus A.
    Simoes, Flavio O.
    Silva, Jose Eduardo C.
    [J]. COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2012, PT I, 2012, 7333 : 240 - 252
  • [15] Eigenfeatures and Supervectors in Feature and Score Fusion for SVM Face and Speaker Verification
    Ejarque, Pascual
    Hernado, Javier
    Hernando, David
    Gomez, David
    [J]. BIOMETRIC ID MANAGEMENT AND MULTIMODAL COMMUNICATION, PROCEEDINGS, 2009, 5707 : 81 - +
  • [16] Improved GMM-UBM/SVM for speaker verification
    Liu, Minghui
    Dai, Beiqian
    Xie, Yanlu
    Yao, Zhiqiang
    [J]. 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13, 2006, : 925 - 928
  • [17] Within-Session Variability Modelling for Factor Analysis Speaker Verification
    Vogt, Robbie
    Pelecanos, Jason
    Scheffer, Nicolas
    Kajarekar, Sachin
    Sridharan, Sridha
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1531 - +
  • [18] Session Variability in Automatic Speaker Verification
    Hayet, Djellali
    Radia, Amirouche
    Akila, Djebbar
    Tayeb, Laskri Mohamed
    [J]. 2014 INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS (ICMCS), 2014, : 185 - 190
  • [19] Combining Deep Speaker Specific Representations with GMM-SVM for Speaker Verification
    Price, Ryan
    Biswas, Sangeeta
    Shinoda, Koichi
    [J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 2787 - 2791
  • [20] MiniVectors: an Improved GMM-SVM Approach for Speaker Verification
    Anguera, Xavier
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2323 - 2326
12345