Rodrigo Mira

Hi, I’m a PhD student at Imperial College London in the Department of Computing, supervised by Maja Pantic and Björn Schuller in IBUG (Intelligent Behaviour Understanding Group). My research is focused on deep learning applied to audio-visual speech (i.e., faces, lip movements and speech). In particular, I am interested in applying self-supervised learning to learn from unlabelled audio-visual speech. I am also interested and have experience in generative modelling, particularly in generating speech using Generative Adversarial Networks (GANs).