Oliver Watts


I am a Research Fellow at the Centre for Speech Technology Research at the University of Edinburgh, currently involved in the Natural Speech Technology project.


My main research interests are exploiting unsupervised and lightly supervised learning to build text-to-speech systems without conventional annotated data, and rapid TTS system development in scarcely-resourced languages. I am more generally interested in using novel linguistic and pragmatic contexts for TTS, and developing appropriate machine learning techniques for effectively incorporating them into systems.


  • See a list of my publications here, complete with downloadable PDFs and citations in Bibtex format.


  • For some demonstrations of TTS systems, see here


  • See here for details of our Ossian TTS tools


  • For details of how to contact me, see here