• DocumentCode
    282034
  • Title

    Fixed point arithmetic in speech recognition systems

  • Author

    Tyler, J.E.M.

  • Author_Institution
    Robert Gordon´´s Inst. of Technol., Aberdeen, UK
  • fYear
    1989
  • fDate
    32660
  • Firstpage
    42644
  • Lastpage
    42646
  • Abstract
    Describes some of the methods used by the author and others in the construction of speech recognisers. The author has implemented some techniques using software written in a high level language, with special functions to implement the fixed point arithmetic processes. A number was represented as a 32 bit integer format, 16 bits for the whole part and 16 bits for the fraction. The techniques implemented were: Levinson-Durbin recursion for LPC calculation; Prime number fast Fourier transform; and cubic spline interpolation for linear time normalisation
  • Keywords
    digital arithmetic; encoding; fast Fourier transforms; ferromagnetic-paramagnetic transitions; interpolation; speech recognition; splines (mathematics); 32 bit; LPC; Levinson-Durbin recursion; Prime number fast Fourier transform; cubic spline interpolation; fixed point arithmetic; high level language; integer format; linear time normalisation; speech recognition systems;
  • fLanguage
    English
  • Publisher
    iet
  • Conference_Titel
    Signal Processing Applications of Finite Field Mathematics, IEE Colloquium on
  • Conference_Location
    London
  • Type

    conf

  • Filename
    198560