• DocumentCode
    1691934
  • Title

    Anti-model KL-SVM-NAP system for NIST SRE 2012 evaluation

  • Author

    Hanwu Sun ; Kong Aik Lee ; Bin Ma

  • Author_Institution
    Inst. for Infocomm Res. (I2R), A*STAR, Singapore, Singapore
  • fYear
    2013
  • Firstpage
    7688
  • Lastpage
    7692
  • Abstract
    This paper presents an anti-model based speaker recognition system for NIST SRE 2012 evaluation, which is one of subsystems in IIR SRE12 submission. We apply the anti-model approach for the SRE12 evaluation. The KL-SVM-NAP based speaker recognition system is adopted to evaluate the performance. We present detailed comparison study of the classical KL-SVM-NAP based speaker recognition system and anti-model based KL-SVM-NAP system for NIST 2012 speaker recognition evaluation. The results are reported on in-house pre-SRE12 development set and NIST SRE12 core task. The clear advantages of the anti-model approach over that the traditional KL-SVM-NAP approach are presented and discussed.
  • Keywords
    learning (artificial intelligence); speaker recognition; support vector machines; IIR SRE12 submission; KL-SVM-NAP based speaker recognition system; NIST SRE 2012 evaluation; anti-model based speaker recognition system; Compounds; NIST; Noise measurement; Speaker recognition; Speech; Support vector machines; Training; Nuisance Attribute Projection; anti-model; speaker recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
  • Conference_Location
    Vancouver, BC
  • ISSN
    1520-6149
  • Type

    conf

  • DOI
    10.1109/ICASSP.2013.6639159
  • Filename
    6639159