{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:31:57Z","timestamp":1780356717469,"version":"3.54.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB2603902"],"award-info":[{"award-number":["2023YFB2603902"]}]},{"name":"Major Science & Technology Specific Project of XINING","award":["2024-Z-7"],"award-info":[{"award-number":["2024-Z-7"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2025.3639371","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T18:51:18Z","timestamp":1764701478000},"page":"201-205","source":"Crossref","is-referenced-by-count":1,"title":["Listening for \u201cYou\u201d: Enhancing Speech Image Retrieval via Target Speaker Extraction"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1019-4446","authenticated-orcid":false,"given":"Wenhao","family":"Yang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-9759","authenticated-orcid":false,"given":"Jianguo","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7951-8907","authenticated-orcid":false,"given":"Wenhuan","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyue","family":"Song","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3527-6034","authenticated-orcid":false,"given":"Xianghu","family":"Yue","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3067"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-96"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022954"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref8","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446418"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3573951"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3591408"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887683"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3507559"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3511268"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625827"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref25","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889085"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-135"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11271847.pdf?arnumber=11271847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T05:53:05Z","timestamp":1766728385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3639371","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}