I'm a PhD student at the Centre for Speech Technology Research in the School of Informatics at the University of Edinburgh, supported by the UKRI CDT in NLP. My supervisors are Korin Richmond and Hao Tang.
My research interests are in text-to-speech synthesis for low-resource languages. I'm interested in finding representations of speech which allow more efficient sharing of information across languages, making it easier to bootstrap training new voices for languages with little annotated data.
- 16/05/22 Our paper Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization received the Best Special Theme Paper award at ACL 2022!
- 13/12/21 Released a simple Kaldi recipe and utility scripts for forced alignment.
- 23/10/21 I presented CSTR's entry to the Blizzard Challenge 2021 task on TTS for code-switched speech in Spanish and English. Audio samples here.
- 28/08/21 I presented my paper on cross-lingual transfer learning for low-resource TTS using phonological feature representations at the 11th ISCA Speech Synthesis Workshop. Audio samples here.