Hi! I’m a Research Scientist at Google DeepMind. I am part of the Winslow team within DeepMind’s Frontier AI organization, where I work with RJ Skerry-Ryan and other talented researchers. Before joining DeepMind, I completed my PhD at the Centre for Speech Technology Research (CSTR) at the University of Edinburgh, under the supervision of Prof. Hao Tang and Prof. Peter Bell.

I'm interested in speech and language processing and machine learning. In particular, my thesis focuses on speech representation learning and speech langauge modeling in the language of discrete latent variable models. I'm also broadly interested in dynamic programming, segmentation, sampling methods and variational learning.