• DocumentCode
    1299667
  • Title

    Speaker identification through use of features selected using genetic algorithm

  • Author

    Haydar, A. ; Demirekler, M. ; Yurtseven, M.K.

  • Author_Institution
    Dept. of Electr. & Electron. Eng., Eastern Mediterranean Univ., Gazu Magosa, Cyprus
  • Volume
    34
  • Issue
    1
  • fYear
    1998
  • fDate
    1/8/1998 12:00:00 AM
  • Firstpage
    39
  • Lastpage
    40
  • Abstract
    The authors introduce the use of a genetic algorithm in the reduction of a 24 parameter (12 LPC derived cepstral coefficients +12 Δ-cepstral coefficients) set to a five, six, seven, eight or ten parameter set, for each speaker in text-independent speaker identification. The experimental results show that there is ~5% increase in the recognition rate when the reduced set of parameters is used
  • Keywords
    feature extraction; genetic algorithms; speaker recognition; LPC; cepstral coefficients; feature selection; genetic algorithm; parameter set; text-independent speaker identification;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19980126
  • Filename
    654505
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1299667