{"url":"/task/audio-to-text-retrieval","name":"Audio to Text Retrieval","slug":"audio-to-text-retrieval","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":10,"papers_with_code":7,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"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/sounddescs","name":"SoundDescs","full_name":"","num_papers_in_archive":8}],"subtasks":[],"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":7,"of":7,"tagged_in_all":10,"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/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/audiosetcaps-an-enriched-audio-caption","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","date":"2024-11-28","arxiv_id":"2411.18953","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/contrastive-audio-language-learning-for-music","title":"Contrastive Audio-Language Learning for Music","date":"2022-08-25","arxiv_id":"2208.12208","repositories_listed":1,"syntology":null},{"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":3,"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"}}