The project and the first prototype of an interface for dictating, recording and printing radiological reports is presented. The most important feature of this interface is multimodality. The radiologist may choose among speech, keyboard and mouse to generate a report. The choice of the input modality depends on the working conditions of the radiologist and the ease and quickness of communication. The motivation for such a project, and the study of the impact of this system on the organisation of the radiologic department in terms of possible improvements in the reporting service, are also presented. The constraints on radiologist-computer speech communication are analyzed. The speech recognizer has been trained on utterances obtained by processing voice reports relative to chest and Ultra Sound (US) examinations. Four users pronounced 100 chest and 20 US reports. This speech material was used as test-data for the automatic speech recognizer. The recognition rate of the speech recognizer, on the two dictionaries, was 98% in the best case and 93% in the worst case.
Bibliographic reference. Antoniol, G. / Brugnara, F. / Palma, F. Dalla / Lazzari, G. / Moser, E. (1991): "A. RE. s. : an interface for automatic reporting by speech", In EUROSPEECH-1991, 973-976.