{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:07:12Z","timestamp":1784131632122,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFC3302800"],"award-info":[{"award-number":["2022YFC3302800"]}]},{"name":"Innovation and Development Joint Funds of Shandong Natural Science Foundation","award":["ZR2022LZH012"],"award-info":[{"award-number":["ZR2022LZH012"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023QF103"],"award-info":[{"award-number":["ZR2023QF103"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3497586","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T18:57:21Z","timestamp":1731524241000},"page":"4945-4960","source":"Crossref","is-referenced-by-count":22,"title":["CLAPSep: Leveraging Contrastive Pre-Trained Model for Multi-Modal Query-Conditioned Target Sound Extraction"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2651-8524","authenticated-orcid":false,"given":"Hao","family":"Ma","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2954-3271","authenticated-orcid":false,"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"ARC Laboratory, Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0659-5765","authenticated-orcid":false,"given":"Mingjie","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-1572","authenticated-orcid":false,"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3160-9233","authenticated-orcid":false,"given":"Ju","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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.2021.3064421"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"ref6","article-title":"Improved speech enhancement with the Wave-U-Net","author":"Macartney","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref8","first-page":"342","article-title":"Decoupling magnitude and phase estimation with deep ResUNet for music source separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Kong","year":"2021"},{"key":"ref9","article-title":"Universal source separation with weakly labelled data","author":"Kong","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref11","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wisdom","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447061"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2210"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref18","article-title":"CLIPSep: Learning text-queried sound separation with noisy unlabeled videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dong","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10894"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447291"},{"key":"ref25","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095266"},{"key":"ref34","article-title":"Typing to listen at the cocktail party: Text-guided target speaker extraction","author":"Hao","year":"2023"},{"key":"ref35","article-title":"Listen, chat, and edit: Text-guided soundscape modification for enhanced auditory experience","author":"Jiang","year":"2024"},{"key":"ref36","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446672"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref42","article-title":"Connect, collapse, corrupt: Learning cross-modal tasks with UNI-modal data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","first-page":"626","article-title":"SDRhalf-baked or well done?","volume-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process.","author":"Roux","year":"2019"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref51","first-page":"69","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset and baseline","volume-title":"Proc. Detection Classification Acoust. Scenes Events","author":"Fonseca","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref53","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref54","first-page":"191","article-title":"A reference-free metric for language-queried audio source separation using contrastive language-audio pretraining","volume-title":"Proc. Detect. Classification Acoust. Scenes Events Workshop","author":"Xiao","year":"2024"},{"issue":"86","key":"ref55","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10752098.pdf?arnumber=10752098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:20:29Z","timestamp":1732663229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3497586","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}