Lipformer: learning to lipread unseen speakers based on visual-landmark transformers
F Xue, Y Li, D Liu, Y Xie, L Wu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Lipreading refers to understanding and further translating the speech of a video speaker into
textual outputs. State-of-the-art lipreading methods excel in interpreting overlap speakers, ie …
textual outputs. State-of-the-art lipreading methods excel in interpreting overlap speakers, ie …