ResearchTasksAudio-visual speech separation and enhancementAudio-visual speech separation and enhancementFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLip2WavAudio-Visual Speech Codec1.482PESQ4Feb 26, 2026FacestarAudio-Visual Speech Codec1.354PESQ4Feb 26, 2026Mandarin dataset (test)VISUALVOICE2.51PESQ4Feb 26, 2026