ResearchTasksAudio Driven Talking Head GenerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRAVDESS (cross-identity)DSM1.885FAD64Apr 23, 2026CREMASonic6.862Sync14Feb 26, 2026MEADWav2lip8.778Sync14Feb 26, 2026HDTF 51 (test)Ground Truth1SSIM9Feb 26, 2026User Study 30 clips (test)MGGTalk37.5Identity Preservation4Feb 26, 2026