GestSync: Determining who is speaking without a talking head
This addresses the challenge of speaker identification in crowds without facial visibility, though it is incremental as it builds on existing synchronisation tasks like Lip-Sync.
The paper tackles the problem of determining if a person's gestures are correlated with their speech, introducing the Gesture-Sync task, and shows that a dual-encoder model can be trained using self-supervised learning on the LRS3 dataset, with applications in audio-visual synchronisation and identifying speakers without facial cues.
In this paper we introduce a new synchronisation task, Gesture-Sync: determining if a person's gestures are correlated with their speech or not. In comparison to Lip-Sync, Gesture-Sync is far more challenging as there is a far looser relationship between the voice and body movement than there is between voice and lip motion. We introduce a dual-encoder model for this task, and compare a number of input representations including RGB frames, keypoint images, and keypoint vectors, assessing their performance and advantages. We show that the model can be trained using self-supervised learning alone, and evaluate its performance on the LRS3 dataset. Finally, we demonstrate applications of Gesture-Sync for audio-visual synchronisation, and in determining who is the speaker in a crowd, without seeing their faces. The code, datasets and pre-trained models can be found at: \url{https://www.robots.ox.ac.uk/~vgg/research/gestsync}.