{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T08:57:51Z","timestamp":1770541071455,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447061","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1446-1450","source":"Crossref","is-referenced-by-count":5,"title":["Audio Prompt Tuning for Universal Sound Separation"],"prefix":"10.1109","author":[{"given":"Yuzhuo","family":"Liu","sequence":"first","affiliation":[{"name":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}]},{"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"}]},{"given":"Yuanyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School"}]},{"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"}]},{"given":"Pingchuan","family":"Tain","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632714"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053396"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10894"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1369"},{"key":"ref6","article-title":"Universal source separation with weakly labelled data","author":"Kong","year":"2023","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01410"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref14","first-page":"334","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","volume-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference","author":"Stoller"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref18","first-page":"159","article-title":"Conditioned-u-net: Introducing a control mechanism in the u-net for multiple source separations","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference","author":"Meseguer-Brocal"},{"key":"ref19","article-title":"Musdb18-a corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447061.pdf?arnumber=10447061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:29:15Z","timestamp":1722576555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447061","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}