Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Radiological Reporting by Speech Recognition: The A.Re.S. System

Bianca Angelini, Giuliano Antoniol, Fabio Brugnara, Mauro Cettolo, Marcello Federico, Roberto Fiutem, Gianni Lazzari

IRST-Istituto per la Ricerca Scientifica e Tecnologica, Povo (Trento), Italy

Radiological reporting has already been identified as a field in which voice technologies can prove to be very useful. Recent progress in automatic speech recognition and in hardware and software technology makes it possible to build large-vocabulary, continuous speech, speaker-independent, real-time systems. In this paper a dictation system for radiology reporting, the A.Re.S. system, is presented. A.Re.S. is a "software only" system which runs in real-time on an HP 715 workstation. It relies on an asynchronous and multi-process architecture in which speech decoding is performed by processes in pipeline. System requirements and architecture will be described, together with the results of a preliminary evaluation based on three months of on-site testing.

Full Paper

Bibliographic reference.  Angelini, Bianca / Antoniol, Giuliano / Brugnara, Fabio / Cettolo, Mauro / Federico, Marcello / Fiutem, Roberto / Lazzari, Gianni (1994): "Radiological reporting by speech recognition: the system", In ICSLP-1994, 1267-1270.