logo BDSP

Base documentaire

  1. Edeka will alle : maschinelle Spracherkennung in der sozialmedizinischen Begutachtung.

    Article - En allemand

    Traduction en anglais : Automatic speech recognition and recording by PC typing systems in socialmedical expertising.

    Automatic speech recognition systems are already being used in spheres employing a restricted vocabulary.


    Our aim was to investigate whether low-cost speech recognition software for PC is capable of being usefully employed in the sphere of sociomedicine.

    Materials and methods 

    To this end 34 representative pages of text (a total of 11,000 words) taken from expertises on cases of suspected medical malpractice (many different subspecialties) were dictated using IBM's « Voice Type Simply Speaking » software.

    Having completed a page, the resulting error rate was recorded, and the text was corrected before we proceeded with the dictation.

    Finally, 3 pages of text were re-dictated and the resulting error rate determined.


    The error rate in the previously unknown text ranged between 10 and 23 per cent (mean 15.9%) without any significant reduction during the training phase, while that in the re-dictated text was drastically reduced to less than 3 per cent.

    It became evident that once a word was corrected the system hardly ever repeated that particular mistake.


    The system's poor performance on unknown text and the missing reduction in the error rate during the training phase are obviously not due to any incompetence of the system but to the huge amount of technical jargon in the scope of medical writing. (...)

    Mots-clés Pascal : Expertise, Reconnaissance parole, Informatique, Ordinateur, Evaluation performance, Qualité, Erreur, Homme

    Mots-clés Pascal anglais : Expertise, Speech recognition, Computer science, Computer, Performance evaluation, Quality, Error, Human

    Logo du centre Notice produite par :
    Inist-CNRS - Institut de l'Information Scientifique et Technique

    Cote : 98-0499429

    Code Inist : 002B30A11. Création : 19/02/1999.