Real-Time Speaker Identification and Participant Tracking in The Access Grid

The Access Grid is a group-to-group videoconferencing technology deployed at over 150 locations worldwide. We believe that there is a need for the Access Grid and other real-time collaboration technologies to provide a richness of interaction that goes beyond just audio, video and simple data sharing. This paper starts by describing in general terms possible extensions to real-time collaboration technology for achieving this and then describes two specific enhancements in the context of the Access Grid, namely speaker identification and participant tracking for the automatic generation of dynamically updated attendance lists. These extensions replace vital perceptual cues lost when videoconferencing, and also have a number of other important benefits, particularly for archiving. We make a case for why these improvements are required in an Access Grid environment and describe current and planned implementation work on a prototype system.

[1]  Mohan M. Trivedi,et al.  Activity monitoring and summarization for an intelligent meeting room , 2000, Proceedings Workshop on Human Motion.

[2]  Roel Vertegaal,et al.  Look who's talking: the GAZE groupware system , 1998, CHI Conference Summary.

[3]  Dan Brickley,et al.  Resource Description Framework (RDF) Model and Syntax Specification , 2002 .

[4]  Rick Stevens,et al.  Access grid: Immersive group-to-group collaborative visualization , 2000 .

[5]  ZHANGLi-xia,et al.  A reliable multicast framework for light-weight sessions and application level framing , 1995 .

[6]  Ralph Gross,et al.  Multimodal Meeting Tracker , 2000, RIAO.

[7]  David De Roure,et al.  Its about time: link streams as continuous metadata , 2001, Hypertext.

[8]  Luc Moreau,et al.  Architectural design of a multi-agent system for handling metadata streams , 2001, AGENTS '01.

[9]  Jessica J. Baldis Effects of spatial audio on memory, comprehension, and preference during desktop conferences , 2001, CHI.

[10]  James A. Hendler,et al.  The Semantic Web" in Scientific American , 2001 .

[11]  Levent M. Arslan,et al.  A sound source classification system based on subband processing , 2002, INTERSPEECH.

[12]  James D. Hollan,et al.  Beyond being there , 1992, CHI.

[13]  Anoop Gupta,et al.  Distributed meetings: a meeting capture and broadcasting system , 2002, MULTIMEDIA '02.

[14]  Nigel Shadbolt,et al.  CoAKTinG: Collaborative Advanced Knowledge Technologies in the Grid , 2002 .