VocaLiST: an audio-visual synchronisation model for lips and voices

Kadandale, Venkatesh S.; Montesinos García, Juan Felipe; Haro Ortega, Gloria

doi:http://dx.doi.org/10.21437/Interspeech.2022-10861

VocaLiST: an audio-visual synchronisation model for lips and voices

Citation

Kadandale VS, Montesinos JF, Haro G. VocaLiST: an audio-visual synchronisation model for lips and voices. In: Proc. Interspeech 2022; 2022 Sep 18-22; Incheon, South Korea. [Baixas]: International Speech Communication Association; 2022. p. 3128-32. DOI: 10.21437/Interspeech.2022-10861

Abstract

In this paper, we address the problem of lip-voice synchronisation in videos containing human face and voice. Our approach is based on determining if the lips motion and the voice in a video are synchronised or not, depending on their audiovisual correspondence score. We propose an audio-visual crossmodal transformer-based model that outperforms several baseline models in the audio-visual synchronisation task on the standard lip-reading speech benchmark dataset LRS2. While the existing methods focus mainly on lip synchronisation in speech videos, we also consider the special case of the singing voice. The singing voice is a more challenging use case for synchronisation due to sustained vowel sounds. We also investigate the relevance of lip synchronisation models trained on speech datasets in the context of singing voice. Finally, we use the frozen visual features learned by our lip synchronisation model in the singing voice separation task to outperform a baseline audio-visual model which was trained end-to-end. The demos, source code, and the pre-trained models are available on https://ipcv.github.io/VocaLiST/