Abstract
In this paper we present the architecture and implementation issues of a dictation machine prototype for medical reports. This machine features a voice recognition input and a voice synthesis output. The physician dictates the results of a medical analysis to the system, controls the construction of the report as well as the system operation by an oral dialogue in natural language. At the end of the dictation, the system generates a written report. In addition to signal processing, voice recognition and synthesis hardware, this prototype has a knowledge-based architecture whose Knowledge Sources perform the dialogue, the syntactic analysis and the semantic analysis of sentences. The entities handled by the system are represented in an object oriented form.
Submitted Version (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call