The vision of immersive environments is to enable natural interactions among people who are geographically distributed. Future interfaces are envisioned to provide some degree of immersion among the user and a device, so as to enable a natural means of interaction. The proliferation of multichannel audio systems (e.g. home-cinema) and of tele-presence systems, which enhance the realism in entertainment and collaborative environments respectively, clearly demonstrate the current technology trend towards immersive environments and interfaces. The winter school aims to cover multiple research directions in audio and speech signal processing for immersive environments and interfaces, including 3D rendering, enhancement in ubiquitous speech communications, speech capture/synthesis/recognition for such applications, audio watermarking in interactive broadcast applications, and so forth.
Among the objectives of the school are:
- Fruitful interaction between teachers/instructors and participants
- Building communities of Ph.D. students and educators in important Signal Processing research areas
- Providing hands-on tutorial sessions, where students can experiment with concepts and methods
- Evolution of high quality tutorial materials that can be disseminated online to the larger signal processing community.