{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:36:24Z","timestamp":1776882984787,"version":"3.51.2"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095266","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":15,"title":["Target Sound Extraction with Variable Cross-Modality Clues"],"prefix":"10.1109","author":[{"given":"Chenda","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref5","article-title":"Voice and accompaniment separation in music using self-attention convolutional neural network","author":"Liu","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2555"},{"key":"ref7","article-title":"Music Source Separation in the Waveform Domain","author":"D\u00e9fossez","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053921"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747722"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003884"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054683"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_21"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548397"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2028"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11183"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","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 ISMIR 2018","author":"Stoller"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref35","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095266.pdf?arnumber=10095266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:38:32Z","timestamp":1709246312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095266","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}