{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T08:02:21Z","timestamp":1780473741983,"version":"3.54.1"},"reference-count":41,"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\/icassp49357.2023.10094573","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":37,"title":["Real-Time Target Sound Extraction"],"prefix":"10.1109","author":[{"given":"Bandhav","family":"Veluri","sequence":"first","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Chan","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malek","family":"Itani","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuochao","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyamnath","family":"Gollakota","sequence":"additional","affiliation":[{"name":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2210"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1369"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3221000"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref8","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref9","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref10","article-title":"Resource-efficient separation transformer","author":"Subakan","year":"2022","journal-title":"arXiv preprint arXiv:2206.09507"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-66"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref13","article-title":"Wildmix dataset and spectro-temporal transformer model for monoaural audio source separation","author":"Zadeh","year":"2019","journal-title":"arXiv preprint arXiv:1911.09783"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref17","article-title":"Environmental sound extraction using onomatopoeic words","author":"Okamoto","year":"2022","journal-title":"ICASSP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538933"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10717"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21394"},{"key":"ref32","article-title":"Semi-supervised time domain target speaker extraction with attention","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2206.09072"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-694"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952149"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref38","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline","author":"Fonseca","year":"2018","journal-title":"DCASE2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref40","article-title":"A multi-device dataset for urban acoustic scene classification","author":"Mesaros","year":"2018","journal-title":"DCASE2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"}],"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\/10094573.pdf?arnumber=10094573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:07:40Z","timestamp":1710367660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094573","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}