The Centre for Speech Technology Research, The university of Edinburgh

AMIDA: Augmented Multiparty Interaction with Distance Access

Project Summary

AMIDA is an EU Integrated Project, following on from AMI, about computer enhanced multi-modal interaction in the context of meetings

Project Details

AMIDA will develop and expand the research vision that we initiated in the EU-IST AMI Integrated Project, to build a new science of human communication. The ground breaking research that we shall undertake in AMIDA will span several traditionally separate disciplines, including: Qualitative human analysis and human factors; Audio-video processing (involving unconstrained speech recognition and natural scene analysis); Multi-modal structure and content analysis; HCI, application prototyping, evaluation, and system integration.

While AMIDA is addressing multiple scientific challenges in the area of multi-modal processing, it also has a large exploitation potential, e.g., in the areas of videoconferencing and collaborative environments, where multiple application prototypes will be integrated and formally evaluated. Finally, through its "Community of Interest" (currently composed of 13 founding members, connected to each other by a shared need to solve common problems, develop skills and share best practices), \AMIDA will also actively engage beyond the consortium to spread awareness and knowledge, and to explore societal implications. AMI and AMIDA are concerned with new multimodal technologies to support human interaction, in the context of instrumented meeting rooms and remote meeting assistants. The project aims to enhance the value of multimodal meeting recordings and to make human interaction more effective in real time. These goals are being achieved by developing new tools for computer supported cooperative work and by designing new ways to search and browse meetings as part of an integrated multimodal group communication, captured from a wide range of devices.

Edinburgh is the joint coordinator of the project (with IDIAP) and researchers from both CSTR and HCRC are involved. Our involvment includes meeting data collection and annotation (using the CSTR Instrumented Meeting Room), speech recognition, microphone arrays, multimodal content extraction, and development and support of the NITE XML annotation toolkit.

Key Edinburgh responsibilities include:

Project homepage:


Funding Source

EU IST programme (Framework VI)