This paper presents an audio-visual approach for voice separation which outperforms state-of-the-art methods at a low latency in two scenarios: speech and singing voice. The model is based on a two-stage network. Motion cues are obtained with a lightweight graph convolutional network that processes face landmarks. Then, both audio and motion features are fed to an audio-visual transformer which produces a fairly good estimation of the isolated target source. In a second stage, the predominant voice is enhanced with an audio-only network. We present different ablation studies and comparison to state-of-the-art methods. Finally, we explore the transferability of models trained for speech separation in the task of singing voice separation. The demos, code, and weights will be made publicly available at https://ipcv.github.io/VoViT/

本文提出了一种音频-视觉声音分离方案，在两种不同场景（语音和唱歌）中实现了低时延的最新成果。该模型基于两级网络，采用轻量级图卷积网络从面部标记中提取运动线索，然后将视觉和音频特征输入到音频-视觉转换器中，为目标源的隔离估计提供相当不错的结果。在第二阶段，利用音频网络增强了主要的声音。我们进行了不同的消融研究和与最先进的方法比较。最后，我们探讨了在唱声分离任务中训练语音分离模型的可转移性。

VoViT: 基于图论的低延迟音视频语音分离Transformer