• DocumentCode
    2007507
  • Title

    An online pronunciation training support system designed for Japanese learners of English

  • Author

    Shudong, Wang ; Higgins, Michael

  • Author_Institution
    Fac. of Eng., Yamaguchi Univ., Japan
  • fYear
    2005
  • fDate
    5-8 July 2005
  • Firstpage
    171
  • Lastpage
    173
  • Abstract
    In this study, a compact but effective Internet-based support system was designed for Japanese English learners to improve their English pronunciation. The system provides several interactive methods for users not only to learn pronunciation from the sample data of native speakers, but also to discover and evaluate their own specific pronunciation problems, and then improve their pronunciation with the help of the system. The system is real-time, Internet based, and the pinpoint feedback from the system after it has analyzed the user´s input sounds, will appear in human teacher-like natural language, rather than impersonal scores or abstract bar graphs which appear in other systems. Our present system focuses on pronunciations that are often problematic for Japanese learners of English. During the process of designing the system, we embedded HMM/DMM speech recognition and speech synthesis modules.
  • Keywords
    Internet; computer aided instruction; hidden Markov models; linguistics; natural languages; real-time systems; speech recognition; speech synthesis; DMM speech recognition; English language; English pronunciation; HMM speech recognition; Internet-based support system; Japanese English learners; feedback; human teacher-like natural language; interactive methods; native speakers; online pronunciation training support system; pronunciation learning; real-time system; speech synthesis; Feedback; Hidden Markov models; Humans; Internet; Loudspeakers; Natural languages; Process design; Real time systems; Speech recognition; Speech synthesis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Learning Technologies, 2005. ICALT 2005. Fifth IEEE International Conference on
  • Print_ISBN
    0-7695-2338-2
  • Type

    conf

  • DOI
    10.1109/ICALT.2005.57
  • Filename
    1508640