 |
The Speech Processing Group of FIT BUT is advised by Prof. Hynek Hermansky,
daily operations of the group are managed by Dr. Jan Cernocky. The group was
formed in 1997 at the Faculty of Electrical Engineering and Computer Science,
as a part of Signal Processing Laboratory, sponsored by the Czech Ministry of
Education. The group has joined the Department of Computer Graphics and
Multimedia of FIT at the creation of FIT in January 2002. The advisor of the
group Prof Hermansky has a significant research and educational track and a
broad industrial and academic experience (US-West, Panasonic, ICSI Berkeley,
OGI Portland). Main expertise of the group is in perceptually-based robust
acoustic processing, speech recognition, keyword spotting and language
identification. The group is also experienced in very low bit rate coding,
automatic determination of speech units and large scale speech database
collection.
In past years, we have participated in EC-sponsored projects aiming at speech
corpora collection - we were the first to coordinate the large-scale collection
of speech data for Czech within the SpeechDat-E project (4th FP,
INCO-Copernicus project No. 977017). As sub-contractors, we have participated
also at SpeeCon (IST-1999-10003), as well as other industry-funded
speech-corpora collection projects. As partner, we have participated in 5th FP
project Multimodal Meeting Manager (M4 - IST-2001-34485) and currently we are a
partner in 6th FP integrated project Augmented Multimodal Interfaces (AMI -
506811). We were granted projects by local funding agencies, namely Grant
Agency of Czech Republic and Ministry of Education of Czech Republic.
The Speech@FIT group disposes of equipment to perform large scale experiments
in speech processing: 2 IBM-Blade servers, each with 12 boards and 24 physical
(48 logical) processors, all running Linux, 4 file servers with total capacity
of 5 TeraBytes and speech and language databases.
|
Update this profile