A multimedia retrieval system using speech input

Andrei Popescu-Belis, Jonathan Kilgour, Peter Poller

In: Proceedings of the 2009 international conference on Multimodal interfaces. International Conference on Multimodal Interfaces (ICMI-2009) November 2-6 Cambridge MA United States Seiten 223-224 ISBN 978-1-60558-772-1 ACM New York 11/2009.


The AMIDA Automatic Content Linking Device (ACLD) monitors a conversation using automatic speech recognition (ASR), and uses the detected words to retrieve documents that are of potential use to the participants in the conversation. The document set that is available includes project related documents such as reports, memos or emails, as well as snippets of past meetings that were transcribed using offline ASR. In addition, results of Web searches are also displayed. Several visualisation interfaces are available.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence