SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision.
Xubo LiuEgor LakomkinKonstantinos VougioukasPingchuan MaHonglie ChenRuiming XieMorrie DoulatyNiko MoritzJáchym KolárStavros PetridisMaja PanticChristian FuegenPublished in: CoRR (2023)