Objective
AMI is concerned with new multimodal technologies to support human interaction, in the context of smart 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 will be 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.
Applications and activities addressed by AMI include:
1. Multimodal input interface: including multilingual speech signal processing and visual input;
2. Integration of modalities and coordination among modalities, including multi-channel processing (eg audio-visual tracking) and multimodal dialogue modelling;
3. Meeting dynamics and human-human interaction modelling, including the definition of meeting scenarios, analysing human interaction and multimodal dialogue modelling;
4. Content abstraction, including multimodal information structuring, indexing, retrieval and summarisation;
5. Collection, management, annotation and sharing of large multimodal meeting recordings via networked media file servers;
6. Technology transfer through exploration and evaluation of advanced end-user applications and prototype systems;
7. Training activities, including an international exchange programme.
This research will be undertaken in the framework of well-defined and complementary application scenarios:
meeting browser; remote meeting assistant; and intregration with wireless presentations.
These demonstrators will be developed on the basis of the smart meeting room and web-enhanced communication infrastructures, which are already available from some of the AMI partners, and which will be extended in multiple ways.
Fields of science
Call for proposal
Data not availableFunding Scheme
IP - Integrated ProjectCoordinator
EH8 9LW EDINBURGH
United Kingdom