Home People Projects Research topics Publications Contact |
The Speech Technology Team (STT) works on developing new methods and approaches to
discovering and processing patterned information within speech and audio signals. The
main focus of STT has been speech analysis, recognition and language acquisition. By
closely following current knowledge related to human cognitive processes, we are striving
to apply this understanding to new technical systems that mimic human behaviour. For this
reason our attention is gradually moving towards multimodal and associative information
processing. Speech corpora form a cornerstone for studying speech. For this reason, the team has long-term experience with modelling speech corpora for efficient access. Multilingual corpora are processed in a uniform and reliable manner, permitting advanced studies to be carried out efficiently. STT has not limited itself to the study of human auditory-based communication exclusively. One interesting area of study has been the recognition of different bird species based on their singing voices. |
Speech Technology Team, 2009 |