{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T01:49:50Z","timestamp":1792115390678,"version":"4.4.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2024.3511414","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:27:56Z","timestamp":1733340476000},"page":"221-225","source":"Crossref","is-referenced-by-count":3,"title":["Text-Based Audio Retrieval by Learning From Similarities Between Audio Captions"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7609-8049","authenticated-orcid":false,"given":"Huang","family":"Xie","sequence":"first","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3641-5377","authenticated-orcid":false,"given":"Khazar","family":"Khorrami","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0537-0946","authenticated-orcid":false,"given":"Okko","family":"R\u00e4s\u00e4nen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4604-9729","authenticated-orcid":false,"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"216","article-title":"Language-based audio retrieval task in DCASE 2022 challenge","volume-title":"Proc. 7th Detection Classification Acoustic Scenes Events 2022 Workshop","author":"Xie","year":"2022"},{"key":"ref2","first-page":"166","article-title":"Improving natural-language-based audio retrieval with transfer learning and audio & text augmentations","volume-title":"Proc. 7th Detection Classification Acoustic Scenes Events 2022 Workshop","author":"Primus","year":"2022"},{"key":"ref3","first-page":"206","article-title":"Matching text and audio embeddings: Exploring transfer-learning strategies for language-based audio retrieval","volume-title":"Proc. 7th Detection Classification Acoustic Scenes Events 2022 Workshop","author":"Weck","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref7","first-page":"151","article-title":"Advancing natural-language based audio retrieval with passt and large audio-caption data sets","volume-title":"Proc. 8th Detection Classification Acoustic Scenes Events 2023 Workshop","author":"Primus","year":"2023"},{"key":"ref8","article-title":"Language-based audio retrieval in DCASE 2023 challenge","year":"2024"},{"key":"ref9","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Kim","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5554-1_1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102688"},{"key":"ref14","first-page":"226","article-title":"Crowdsourcing and evaluating text-based audio retrieval relevances","volume-title":"Proc. 8th Detection Classification Acoustic Scenes Events 2023 Workshop","author":"Xie","year":"2023"},{"key":"ref15","first-page":"201","article-title":"Integrating continuous and binary relevances in audio-text relevance learning","volume-title":"Proc. 9th Detection Classification Acoust. Scenes Events Workshop","author":"Xie","year":"2024"},{"key":"ref16","first-page":"121","article-title":"Estimated audio-caption correspondences improve language-based audio retrieval","volume-title":"Proc. 9th Detection Classification Acoust. Scenes Events Workshop","author":"Primus","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref18","article-title":"Image-text retrieval with binary and continuous label supervision","author":"Li","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111431"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref21","article-title":"BBC sound Effects","year":"2024"},{"key":"ref22","article-title":"SoundBible","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref24","article-title":"Language-based audio retrieval in DCASE 2024 challenge","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref26","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref27","article-title":"Representation learning with contrastive predictive coding","author":"Den","year":"2018"},{"key":"ref28","first-page":"1769","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10777565.pdf?arnumber=10777565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T05:21:16Z","timestamp":1738387276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3511414","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}