Universität Bielefeld - Sonderforschungsbereich 360
A Knowledge-based System Integrating Speech and Image Understanding - Manual
Version 1.0 -
Gudrun Socher and Uta Naeve
Abstract
We presend a system that integrates speech and images understanding in the domain
of a construction task. Knowledge needed to interpret speech and images is stored
in one homogeneous knowledge base using the semantic network formalism ERNEST.
It provides a means for constraint propagation and therefore - using a uniform
representation of the information gained from real input data - the speech and image
understanding processes can profit from each other. Even preliminary results are used
to restrict the number of valid interpretations. Examples illustrate the flexibility
and the performance of our integrated system.
Anke Weinberger, 1996-08-23