AV-HuBERT (Audio-Visual Hidden Unit BERT)

AV-HuBERT is a self-supervised representation learning framework for audio-visual speech.

Github: https://github.com/facebookresearch/av_hubert

Facebook AI: https://ai.facebook.com/blog/ai-that-understands-speech-by-looking-as-well-as-hearing/

Paper: https://arxiv.org/abs/2201.02184

👉 @bigdata_1