Semantic and Phonetic Automatic Reconstruction of Medical Dictations

Stefan Petrik (1) , Christina Drexel , Leo Fessler , Jeremy Jancsary (2) , Alexandra Klein (2) , Gernot Kubin (1) , Johannes Matiasek (2) , Franz Pernkopf (1) , Harald Trost (3)

1 TU Graz - Graz University of Technology [Graz]
2 OFAI - Austrian Research Institute for Artificial Intelligence
3 Institute of Medical Cybernetics and Artificial Intelligence of the Center for Brain

Automatic speech recognition (ASR) has become a valuable tool in large document production environments like medical dictation. While manual post-processing is still needed for correcting speech-recognition errors and for creating documents which adhere to various stylistic and formatting conventions, a large part of the document production process is carried out by the ASR system. For improving the quality of the system output, knowledge about the multi-layered relationship between the dictated texts and the final documents is required. Thus, typical speechrecognition errors can be avoided, and proper style and formatting can be anticipated in the ASR part of the document-production process. Yet - while vast amounts of recognition results and manually edited final reports are constantly being produced - the error-free literal transcripts of the actually dictated texts are a scarce and costly resource because they have to be created by manually transcribing the audio files.

Mots clés: Physical Sciences

Domaines: Linguistique

Stefan Petrik, Christina Drexel, Leo Fessler, Jeremy Jancsary, Alexandra Klein, et al.. Semantic and Phonetic Automatic Reconstruction of Medical Dictations. Computer Speech and Language, 2010, 25 (2), pp.363. ⟨10.1016/j.csl.2010.07.003⟩. ⟨hal-00692188⟩