Ton Kalker, TIFS TC
Gokhan Tur, SLP TC
Zhengyou Zhang, MMSP TC
Srinivas Bangalore, SLP TC
Yannis Stylianou, SLP TC
With the advent of modern communication technology, physical distance is no longer a barrier to real-time interaction. But current technologies are not perfect: cellular networks typically lack a video component; broadband connections hardly provide for an immersive experience; high-end remote presence solutions are expensive and constraining. Therefore there is a strong need of research and development of advanced technologies and tools to bring immersive experience into teleconferencing so people across geographically distributed sites can interact collaboratively. This requires deep understanding of multiple disciplines. The Immersive Communication TS touches the topics of user experience, speech processing, 3D video, and multi-modal processing.
PLEN-3: Cognitive User Interfaces: an Engineering Approach
by Steve Young, University of Cambridge
Chairs: Ton Kalker, TIFS, Hewlett-Packard and Zhengyou Zhang, MMSP, Microsoft
Title: Speech Enhancement by Conditional Estimation: Noise Reduction, Error Concealment & Bandwidth Extension, what makes the difference?
Speaker: Peter Vary, RWTH Aachen University, Germany
Title: Cooperative Team Behavior Recognition for Multimodal Fusion
Speaker: Benoit Macq, Universite Catholique Louvain, Louvain, Belgium
Title: Video processing for immersive communication
Speaker: Wen Gao, Beijing University, Beijing, China
SS-L9: Handling Reverberant Speech: Methodologies and Applications
AE-L4: Microphone and Loudspeaker Array Signal Processing
IVMSP-L5: Stereoscopic and 3-D Processing
SPE-L6: Speech Enhancement I
SPE-L11: Speech Enhancement III
AE-P3: Acoustic Echo Control and Microphone Array Signal Processing
MMSP-P1: Multimodal Systems & Applications
SPTM-P3: Source Separation