• DocumentCode
    431327
  • Title

    Speaker Detection Without Models

  • Author

    Gillick, Daniel ; Stafford, Stephen ; Peskin, Barbara

  • Author_Institution
    Int. Comput. Sci. Inst., Berkeley, CA, USA
  • Volume
    1
  • fYear
    2005
  • fDate
    March 18-23, 2005
  • Firstpage
    757
  • Lastpage
    760
  • Keywords
    Gaussian processes; error statistics; learning (artificial intelligence); speaker recognition; GMM; Gaussian mixture model; error rates; extended training data conditions; scoring method; sequential information; speaker detection; speech recognizer; Acoustic testing; Automatic speech recognition; Cepstral analysis; Computer science; Error analysis; Hidden Markov models; Loudspeakers; NIST; Sequential analysis; Training data;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
  • ISSN
    1520-6149
  • Print_ISBN
    0-7803-8874-7
  • Type

    conf

  • DOI
    10.1109/ICASSP.2005.1415224
  • Filename
    1415224