Rithesh Kumar

I am a Master’s student at MILA, supervised by Prof. Yoshua Bengio.

I’ve previously worked on generative models for speech (https://arxiv.org/abs/1612.07837) with MILA, and Lyrebird.ai

I recently worked on creating photo-realistic talking head models from text, with the research work – ‘ObamaNet – Photo-realistic lip-sync from text’, presented as an oral presentation at NIPS 2017 ML for Creativity and Design workshop.

I’m currently interested in generative models for language, collaborating with Microsoft Research – Montreal.