I am a senior research scientist at a London-based AI tech company Flawless AI. I am also a visiting research fellow based in the Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey. I currently work in developing AI methods to generate photo-realistic face animation from speech, i.e. audio driven face animation, and also various speech-related inititives such as multi-modal speech editing, immersive audio, synthetic audio.