The Speech Group at the Department of Speech, Music and Hearing at the KTH School of Computer Science and Communication has an excellent academic record in the field of speech communication and speech technology, dating back to the 1950s. The research group’s strong international standing is evidenced by a wide participation in more than 20 EU projects including the database-related projects SpeechDat, SPEECON, and CLARIN. Current research focusses on detecting, describing, interpreting, modelling and synthesizing interactional aspects of spoken face-to-face communication with applications in spoken dialogue systems and robotics.
The group has an equally long-standing record in developing speech technology software (e.g. several text-to-speech systems, including one of the earliest multilingual systems; a number of speech analysis tools, including a widely used tool for speech annotation and visualization and a dialogue annotation tool).
As a type K center, KTH will provide expertise in the collection, processing, annotation and exploitation of large multimodal speech corpora as exemplified by the Spontal corpus (60 hours of synchronized audio, video, and three-dimensional motion-capture data in unconstrained human–human conversations). Studies of such speech and dialogue corpora will enable and benefit a wide variety of related research activities in the humanities and social sciences, ranging from speech and gesture research to studies of behaviour and social signals in human communication and interaction.
Contact: David House, davidh (at) csc.kth.se