• DocumentCode
    3140748
  • Title

    Data-Driven Approach to Pronunciation Error Detection for Computer Assisted Language Teaching

  • Author

    Liang, Min-Siong ; Hong, Zien-Yong ; Lyu, Ren-Yuan ; Chiang, Yuang-chin

  • Author_Institution
    Chang Gung Univ., Taoyuan
  • fYear
    2007
  • fDate
    18-20 July 2007
  • Firstpage
    359
  • Lastpage
    361
  • Abstract
    This paper describes an approach to pronunciation error detection for computer-assisted pronunciation teaching (CAPT). We focus on how to find the real pronunciation of the user. The data-driven based method was used to generate pronunciation errors hypotheses instead of knowledge-based method. In the experiment results, the error rate of pronunciation detection can achieve 10.56%. Finally, we applied this technique into our CAPT system.
  • Keywords
    computer aided instruction; linguistics; teaching; computer assisted language teaching; data-driven approach; knowledge-based method; pronunciation error detection; Computer errors; Computer science; Education; Error analysis; Flowcharts; Hidden Markov models; Natural languages; Speech recognition; Speech synthesis; Stress;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Learning Technologies, 2007. ICALT 2007. Seventh IEEE International Conference on
  • Conference_Location
    Niigata
  • Print_ISBN
    0-7695-2916-X
  • Type

    conf

  • DOI
    10.1109/ICALT.2007.111
  • Filename
    4281035