ResearchDatasetsAudioCaps, Clotho, and MECATAudioCaps, Clotho, and MECATFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsText-to-Text Retrieval (T2T)AudioCaps, Clotho, and MECAT Mean46.46R@113Text-to-Audio Retrieval (T2A)AudioCaps, Clotho, and MECAT Mean0.221Recall@113