• DocumentCode
    1280983
  • Title

    Improvement of the synthesised speech intonation with stylisation and neural network learning

  • Author

    Lee, Jung-Chul ; Sung, Koeng-Mo

  • Author_Institution
    Electron. & Telecommun. Res. Inst., Taejon, South Korea
  • Volume
    33
  • Issue
    19
  • fYear
    1997
  • fDate
    9/11/1997 12:00:00 AM
  • Firstpage
    1600
  • Lastpage
    1601
  • Abstract
    A new F0 contour generation model with stylisation and neural network learning is proposed. Our F0 contour consists of (i) global tune, (ii) word pitch bias, (iii) lexical tone, and (iv) syllabic pitch pattern. A preconstructed melodic table takes care of (i), (ii) and (iv) while a neural network deals with (iii). A 5-level subject test shows 0.5 point intonation quality improvement compared to our previous model
  • Keywords
    learning (artificial intelligence); neural nets; speech synthesis; F0 contour generation model; global tune; intonation quality improvement; lexical tone; neural network learning; preconstructed melodic table; stylisation; syllabic pitch pattern; synthesised speech intonation; word pitch bias;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19971081
  • Filename
    629579
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1280983