• DocumentCode
    2608498
  • Title

    Intelligibility of Children with Cleft Lip and Palate: Evaluation by Speech Recognition Techniques

  • Author

    Maier, Andreas ; Hacker, Christian ; Nöth, Elmar ; Nkenke, Emeka ; Haderlein, Tino ; Rosanowski, Frank ; Schuster, Maria

  • Author_Institution
    Lehrstuhl fur Mustererkennung, Univ. Erlangen-Nurnberg, Erlangen
  • Volume
    4
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    274
  • Lastpage
    277
  • Abstract
    Cleft lip and palate (CLP) may cause functional limitations even after adequate surgical and non-surgical treatment, speech disorder being one of them. Until now, an objective means to determine and quantify the intelligibility does not exist. An automatic speech recognition system was applied to 31 recordings of CLP children who spoke a German standard test for articulation disorders. The speech recognition system was trained with normal adult speakers´ and children´s speech. A subjective evaluation of the intelligibility was performed by a panel of 3 experts and confronted to the automatic speech evaluation. The automatic speech recognition yielded word accuracies between 1.2% and 75.8% (48.0% plusmn 19.6%) with sufficient discrimination. It complied with experts´ rating of intelligibility. Thus we show that automatic speech recognition serves as a good means to objectify and quantify global speech outcome of children with CLP
  • Keywords
    speech intelligibility; speech recognition; German language; articulation disorders; automatic speech recognition; cleft lip and palate children; speech disorder; Automatic speech recognition; Automatic testing; Birth disorders; Computer hacking; Hidden Markov models; Pattern recognition; Speech analysis; Speech recognition; Surgery; Tongue;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-2521-0
  • Type

    conf

  • DOI
    10.1109/ICPR.2006.718
  • Filename
    1699833