ResearchTasksAudio-driven talking face generationAudio-driven talking face generationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedUser StudyPC-Talk4.6Lip-sync Accuracy7Jun 5, 2026CelebV (randomly sampled 50 videos)IMTalker17.921FID6Feb 26, 2026HDTF (randomly sampled 50 videos)IMTalker9.084FID6Feb 26, 2026OneMin-32VASA-17.99Sc6Feb 26, 2026VoxCeleb2VASA-18.841Sc6Feb 26, 2026