• DocumentCode
    1852600
  • Title

    TETRA channel simulation for automatic speech recognition

  • Author

    Stein, Daniel ; Winkler, Thomas ; Schwenninger, Jochen ; Bardeli, Rolf

  • Author_Institution
    Fraunhofer Inst. for Intell. Anal. & Inf. Syst., St. Augustin, Germany
  • fYear
    2012
  • fDate
    27-31 Aug. 2012
  • Firstpage
    1653
  • Lastpage
    1657
  • Abstract
    The problem of deterioated automatic speech recognition performance for telecommunication devices like mobile phones is well-studied. However, few papers analyse the influence of emergency broadcast radio devices such as the Terrestrial Trunked Radio (TETRA), which is used for many public safety networks in Europe and Asia. In this paper, we dissect several aspects of the TETRA encoding scheme when transmitting over a dedicated emergency radio station by conducting experiments with original hardware and corresponding software simulations. We also offer a new technique for a cepstral mismatch compensation.
  • Keywords
    encoding; mobile handsets; radio broadcasting; radio equipment; speech recognition; Asia; Europe; TETRA channel simulation; TETRA encoding scheme; automatic speech recognition performance; cepstral mismatch compensation; emergency broadcast radio devices; emergency radio station; mobile phones; public safety networks; software simulations; telecommunication devices; terrestrial trunked radio; Cepstral analysis; Codecs; Feature extraction; Harmonic distortion; Noise; Speech; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Conference (EUSIPCO), 2012 Proceedings of the 20th European
  • Conference_Location
    Bucharest
  • ISSN
    2219-5491
  • Print_ISBN
    978-1-4673-1068-0
  • Type

    conf

  • Filename
    6334083