• DocumentCode
    1152612
  • Title

    What jumbo tells dumbo

  • Author

    Antunes, Alden

  • Volume
    7
  • Issue
    5
  • fYear
    2005
  • Firstpage
    3
  • Lastpage
    6
  • Abstract
    What do elephants and humans have in common? According to Marquette University´s Patrick Clemins, individuals in both species have distinct voices, and we can train computers to recognize 85 percent of what they say. Running preidentified elephant sounds into a PC-based hidden Markov model (HMM) algorithm trains that program to then recognize and classify further elephant recordings. In short, combine a herd of six elephants´ a digital tape deck, and a basic workstation running an HMM, and you get the start of a great conversation. The software´s accuracy not only bests human efforts for elephant speech, but it´s also comparable with the same task - using the same approach and software - done on human speech.
  • Keywords
    audio signal processing; biocommunications; biology computing; hidden Markov models; speech processing; speech recognition; zoology; HMM algorithm; PC-based hidden Markov model; elephant sounds; human speech; speech classification; speech recognition; conversation; match; noise;
  • fLanguage
    English
  • Journal_Title
    Computing in Science & Engineering
  • Publisher
    ieee
  • ISSN
    1521-9615
  • Type

    jour

  • DOI
    10.1109/MCSE.2005.106
  • Filename
    1501732