{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:38:09Z","timestamp":1777477089643,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887543","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Language-Queried Target Sound Extraction Without Parallel Training Data"],"prefix":"10.1109","author":[{"given":"Hao","family":"Ma","sequence":"first","affiliation":[{"name":"Shandong University,School of Information Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"North Carolina State University,Department of Computer Science,North Carolina,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukai","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University,School of Information Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Shao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Key Laboratory of System and Control, AMSS,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University,School of Information Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref6","first-page":"342","article-title":"Decoupling magnitude and phase estimation with deep ResUNet for music source separation","volume-title":"Proc. Int. Conf. Music Inf. Retr. (ISMIR)","author":"Kong"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref8","article-title":"Universal source separation with weakly labelled data","author":"Kong","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095128"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3520017"},{"key":"ref17","article-title":"CLIPSep: Learning text-queried sound separation with noisy unlabeled videos","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref21","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448115"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref24","article-title":"Connect, collapse, corrupt: Learning cross-modal tasks with uni-modal data","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref26","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Liang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref30","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. N. Am. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol. (NAACL-HLT)","author":"Kim"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887543.pdf?arnumber=10887543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:07Z","timestamp":1774416187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887543","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}