The Signal Processing Laboratory of the Institute of Computer Science (ICS) of the
Foundation for Research and Technology – Hellas (FORTH) organized the international
Winter School on Speech and Audio Processing for Immersive Environments and Future
Interfaces of the IEEE Signal Processing Society (IEEE SPS Winter School on SAIE
2012, http://www.s3p-saie.eu/), which took place from January 16th to 20th 2012, at
FORTH, in Heraklion Crete, Greece.

The Winter School involved a series of lectures from distinguished researchers from
all over the world and was focused on current research trends and applications in the
areas of audio and speech signal processing. More specifically, current trends were
presented in areas such as automatic speech recognition, speech synthesis, speech and
audio modeling and coding, speech capture in noisy environments using one or more
microphones, and 3D audio rendering using 2 or more loudspeakers. The Winter School
also involved “hands-on” sessions, where students were able to work on practical aspects
of speech and audio signal processing, as well as "demo" sessions where researchers
from FORTH and other institutes demonstrated their implemented systems in these fields.

Many of the technologies that were presented in the school will be implemented and
demonstrated in the context of the Ambient Intelligence (AmI) Program of FORTH-
ICS. Specifically, sound-related technologies, which are a natural means of human-
computer interaction in AmI environments, will be developed and demonstrated in
a new laboratory space for 3D sound rendering and recording, to be included in an
under-construction building on the FORTH campus which will be dedicated to AmI
technologies.

This Winter School is the 4th in the Series of "Seasonal Schools in Signal Processing"
(S3P Program) of the IEEE Signal Processing Society. Previous Seasonal Schools
were organized in The Netherlands, Austria, and Taiwan. In the Winter School at
FORTH, forty students and professionals participated from all around the world, with the
opportunity to attend lectures taught by world-renowned researchers and to have a close
interaction with them, but also to meet each other to strengthen the audio and speech
research community.