Our main areas of interest are speech, vision and language processing, machine learning and interaction.
The purpose of our research is to investigate how humans process speech, language and vision, and to design mathematical models for automatic processing that can be used with communicating machines.
Our studies rely on computational models from batch or on-line examples and provide predictive models for data classification, automatic sequence labelling and structure inference.
Another research area the group is involved in is human-centered communication systems. We investigate models of interactions in any ICT scenario, such as speech-to-speech, speech-to-web and multimodal interactions. Our focus is both on the computational aspect of the interaction models as well as on the usability of user interfaces.
Finally, we also devote our attention to collaborative systems and web architecture. We are active in the design of software architecture for advanced web and multimedia collaborative systems.