{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/audio-retrieval-with-natural-language-queries","title":"Audio Retrieval with Natural Language Queries","arxiv_id":"2105.02192","date":"2021-05-05","proceeding":null,"authors":["Andreea-Maria Oncescu","A. Sophia Koepke","João F. Henriques","Zeynep Akata","Samuel Albanie"],"abstract":"We consider the task of retrieving audio using free-form natural language queries. To study this problem, which has received limited attention in the existing literature, we introduce challenging new benchmarks for text-based audio retrieval using text annotations sourced from the Audiocaps and Clotho datasets. We then employ these benchmarks to establish baselines for cross-modal audio retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into cross-modal text-based audio retrieval with free-form text queries.","url_abs":"https://arxiv.org/abs/2105.02192v2","url_pdf":"https://arxiv.org/pdf/2105.02192v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"audio-retrieval-with-natural-language-queries","repo_url":"https://github.com/oncescuandreea/audio-retrieval","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-to-text-retrieval","task_name":"Audio to Text Retrieval"},{"task_slug":"audio-video-to-text-retrieval","task_name":"Audio/Video to Text Retrieval"},{"task_slug":null,"task_name":"AudioCaps"},{"task_slug":"form","task_name":"Form"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-to-audio-retrieval","task_name":"Text to Audio Retrieval"},{"task_slug":"text-to-audio-video-retrieval","task_name":"Text to Audio/Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","task":"Text to Audio Retrieval","dataset":"AudioCaps","model":"CE","rank_in_archive_order":9,"of":11,"metrics":{"R@1":"23.1±0.8\t","R@10":"70.7±0.7"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","task":"Text to Audio Retrieval","dataset":"AudioCaps","model":"MoEE","rank_in_archive_order":11,"of":11,"metrics":{"R@1":"22.5±0.3\t","R@10":"69.5±0.9\t"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset":"Clotho","model":"CE (pretraining:AudioCaps)","rank_in_archive_order":7,"of":12,"metrics":{"R@1":"9.6±0.3\t","R@10":"40.1±0.7\t"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset":"Clotho","model":"MoEE (pretraining:AudioCaps)","rank_in_archive_order":8,"of":12,"metrics":{"R@1":"8.6±0.4\t","R@10":"39.3±0.7\t"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset":"Clotho","model":"CE","rank_in_archive_order":9,"of":12,"metrics":{"R@1":"6.7±0.4\t","R@10":"33.2±0.3\t"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset":"Clotho","model":"MoEE","rank_in_archive_order":12,"of":12,"metrics":{"R@1":"6.0±0.1\t","R@10":"32.3±0.3\t"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.02192","atlas_url":"https://app.syntology.ai/?focus=2105.02192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02192"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oncescuandreea/audio-retrieval","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fc6aa51656b4be1e","entry":"kronecker_prod","repo":"oncescuandreea/audio-retrieval","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/oncescuandreea/audio-retrieval/blob/HEAD/model/model.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc6aa51656b4be1e"}},{"code_sha256_prefix":"a5a7db2dc3069c5d","entry":"retrieval_as_classification","repo":"oncescuandreea/audio-retrieval","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/oncescuandreea/audio-retrieval/blob/HEAD/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5a7db2dc3069c5d"}},{"code_sha256_prefix":"c5497b09ac6e500b","entry":"t2v_metrics","repo":"oncescuandreea/audio-retrieval","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/oncescuandreea/audio-retrieval/blob/HEAD/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c5497b09ac6e500b"}},{"code_sha256_prefix":"382b08bd2c7acdef","entry":"v2t_metrics","repo":"oncescuandreea/audio-retrieval","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/oncescuandreea/audio-retrieval/blob/HEAD/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"382b08bd2c7acdef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}