joonson

syncnet_python. Out of time: automated lip sync in the wild

voxconverse. Spot the conversation: speaker diarisation in the wild

syncnet_trainer. Disentangled Speech Embeddings using Cross-Modal Self-Supervision

voxceleb_unsupervised. Augmentation adversarial training for self-supervised speaker recognition

yousaidthat. You Said That?: Synthesising Talking Faces from Audio

voxsrc_2019. VoxSRC Challenge

voxceleb_trainer. In defence of metric learning for speaker recognition