astorfi/3D-convolutional-Audio-Visual

:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

13 best points · 6 comments · 2 Hacker News posts · 1,906 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Lip Reading – Who Said What? Answered by Deep Learning (13 points, 6 comments, by irsina, 2017-07-15)
• Lip Reading – Who Said What? Implementation in TensorFLow and Python (3 points, 0 comments, by irsina, 2017-07-15)