• DocumentCode
    528670
  • Title

    Spoken language identification based on GMM models

  • Author

    Dustor, Adam ; Szwarc, Pawel

  • Author_Institution
    Inst. of Electron., Silesian Univ. of Technol., Gliwice, Poland
  • fYear
    2010
  • fDate
    7-10 Sept. 2010
  • Firstpage
    105
  • Lastpage
    108
  • Abstract
    The paper describes application of gaussian mixture models GMM to the task of spoken language identification. The influence of the length of the test utterances on identification error rate was examined. During identification procedure recordings for 15 languages were used, both European and Asian ones. As a language model GMM with full covariance matrix was applied. Obtained results of identification error rate were discussed.
  • Keywords
    Gaussian processes; covariance matrices; natural language processing; speech recognition; GMM models; Gaussian mixture models; covariance matrix; identification error rate; identification procedure recordings; language model GMM; spoken language identification; test utterances; Covariance matrix; Feature extraction; Read only memory; Speech; Speech recognition; Testing; Training;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signals and Electronic Systems (ICSES), 2010 International Conference on
  • Conference_Location
    Gliwice
  • Print_ISBN
    978-1-4244-5307-8
  • Electronic_ISBN
    978-83-9047-4-2
  • Type

    conf

  • Filename
    5595243