Jeongsoo Choi, Joanna Hong, Yong Man Ro. DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 7778-7787, IEEE, 2023. [doi]
Abstract is missing.