Visualization Metaphors for Multi-modal Meeting Data

The MISTRAL system, a service oriented architecture for semantic extraction of multimedia data from meeting recordings is described shortly. It improves on other similar systems by extracting a variety of semantic metadata from one media type and integrating it with concepts derived from other media types, as well as by adding inference capabilities to resolve ambiguities and further enrich extracted data. On top of this state-of-the-art extraction functionality a number of semantic-based, cross-modal visual applications for exploration and retrieval of extraction results were developed. Three selected applications, implemented upon the MISTRAL’s semantic application architecture, are presented and described into detail in this paper.