• DocumentCode
    699915
  • Title

    Contribution to statistical acoustic-to-EMA mapping

  • Author

    Toutios, Asterios ; Margaritis, Konstantinos

  • Author_Institution
    LORIA, Vandœuvre-lès-Nancy, France
  • fYear
    2008
  • fDate
    25-29 Aug. 2008
  • Firstpage
    1
  • Lastpage
    5
  • Abstract
    The availability of large corpora of parallel acoustic and articulatory data has enabled the use of statistical, data-driven, methods in the context of the speech inversion problem. This paper explores the use of Support Vector Regression for the mapping from acoustic parameters to electromagnetic articulograph trajectories and compares the outcoming results against those presented in other studies on the same problem and dataset.
  • Keywords
    regression analysis; speech processing; support vector machines; acoustic parameters; electromagnetic articulograph trajectories; speech inversion problem; statistical acoustic-to-EMA mapping; support vector regression; Acoustics; Coils; Speech; Support vector machines; Training; Trajectory; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Conference, 2008 16th European
  • Conference_Location
    Lausanne
  • ISSN
    2219-5491
  • Type

    conf

  • Filename
    7080447
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=699915