{"url":"/task/text-to-audio-retrieval","name":"Text to Audio Retrieval","slug":"text-to-audio-retrieval","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":20,"papers_with_code":13,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","slug":"text-to-audio-retrieval-on-clotho","dataset":"Clotho","dataset_url":"/dataset/clotho","rows_in_archive":12,"metrics":["R@1","R@5","R@10","mAP@10"],"first_row_in_archive_order":{"model":"PaSST-RoBERTa & Estimated Audio–Caption Correspondences","paper_title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","paper_url":"/paper/estimated-audio-caption-correspondences","paper_date":"2024-08-21","arxiv_id":"2408.11641","code_links":[{"title":"optimusprimus/salsa","url":"https://github.com/optimusprimus/salsa"}],"syntology":null}},{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","slug":"text-to-audio-retrieval-on-audiocaps","dataset":"AudioCaps","dataset_url":"/dataset/audiocaps","rows_in_archive":11,"metrics":["R@1","R@5","R@10"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/text-to-audio-retrieval-on-sounddescs","slug":"text-to-audio-retrieval-on-sounddescs","dataset":"SoundDescs","dataset_url":"/dataset/sounddescs","rows_in_archive":4,"metrics":["R@1","R@10"],"first_row_in_archive_order":{"model":"CE","paper_title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","paper_url":"/paper/audio-retrieval-with-natural-language-queries-1","paper_date":"2021-12-17","arxiv_id":"2112.09418","code_links":[{"title":"akoepke/audio-retrieval-benchmark","url":"https://github.com/akoepke/audio-retrieval-benchmark"}],"syntology":null}},{"leaderboard":"/sota/text-to-audio-retrieval-on-localized","slug":"text-to-audio-retrieval-on-localized","dataset":"Localized Narratives","dataset_url":"/dataset/localized-narratives","rows_in_archive":1,"metrics":["Text-to-audio R@1","Text-to-audio R@10","Text-to-audio R@5"],"first_row_in_archive_order":{"model":"OPT","paper_title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","paper_url":"/paper/opt-omni-perception-pre-trainer-for-cross","paper_date":"2021-07-01","arxiv_id":"2107.00249","code_links":[{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/mm/opt"},{"title":"2023-MindSpore-1/ms-code-161","url":"https://github.com/2023-MindSpore-1/ms-code-161"}],"syntology":null}}],"datasets":[{"url":"/dataset/audiocaps","name":"AudioCaps","full_name":"","num_papers_in_archive":279},{"url":"/dataset/clotho","name":"Clotho","full_name":"Clotho","num_papers_in_archive":202},{"url":"/dataset/localized-narratives","name":"Localized Narratives","full_name":"","num_papers_in_archive":63},{"url":"/dataset/wavcaps","name":"WavCaps","full_name":"","num_papers_in_archive":41},{"url":"/dataset/sounddescs","name":"SoundDescs","full_name":"","num_papers_in_archive":8}],"subtasks":[{"url":"/task/audio-moment-retrieval","name":"audio moment retrieval"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":13,"of":13,"tagged_in_all":20,"items":[{"url":"/paper/m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":15,"n_unverified":27,"n_pointer_only":0}},{"url":"/paper/one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/opt-omni-perception-pre-trainer-for-cross","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","date":"2021-07-01","arxiv_id":"2107.00249","repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-of-pretrained-language-models-on","title":"Evaluation of pretrained language models on music understanding","date":"2024-09-17","arxiv_id":"2409.11449","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/estimated-audio-caption-correspondences","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","date":"2024-08-21","arxiv_id":"2408.11641","repositories_listed":1,"syntology":null},{"url":"/paper/the-song-describer-dataset-a-corpus-of-audio","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","date":"2023-11-16","arxiv_id":"2311.10057","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/advancing-natural-language-based-audio","title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","date":"2023-08-08","arxiv_id":"2308.04258","repositories_listed":1,"syntology":null},{"url":"/paper/valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-retrieval-with-querybank","title":"Cross Modal Retrieval with Querybank Normalisation","date":"2021-12-23","arxiv_id":"2112.12777","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/audio-retrieval-with-natural-language-queries-1","title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","date":"2021-12-17","arxiv_id":"2112.09418","repositories_listed":1,"syntology":null},{"url":"/paper/audio-retrieval-with-natural-language-queries","title":"Audio Retrieval with Natural Language Queries","date":"2021-05-05","arxiv_id":"2105.02192","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}