The Centre for Speech Technology Research, The university of Edinburgh


Our current research covers speech recognition, speech synthesis, speech signal processing, information access, multimodal interfaces, dialogue systems, machine learning and acoustic phonetics.

Complete list of CSTR publications.

Current projects

Previous projects are listed in the Project Archive.


Two corpora recorded at the CSTR are available through the LDC, these are:

The MC-WSJ-AV and 2012_MMA corpus data are managed by the LDC. For more details see LDC (Linguistic Data Consortium)


Much of our research is released within open source software toolkits. CSTR researchers contribute to three major toolkits in particular:

Seminar schedules

International conference schedules