{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:10:48Z","timestamp":1776885048001,"version":"3.51.2"},"reference-count":40,"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\/icassp48485.2024.10446032","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"446-450","source":"Crossref","is-referenced-by-count":11,"title":["Boosting Unknown-Number Speaker Separation with Transformer Decoder-Based Attractor"],"prefix":"10.1109","author":[{"given":"Younglo","family":"Lee","sequence":"first","affiliation":[{"name":"42dot Inc.,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shukjae","family":"Choi","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700814"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-700"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096646"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/605"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1550"},{"key":"ref22","first-page":"3735","article-title":"Sequence to multi-sequence learning via conditional chain mapping for mixture signals","volume-title":"Proc. NIPS","volume":"33","author":"Shi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2418"},{"key":"ref24","first-page":"7121","article-title":"Voice separation with an unknown number of multiple speakers","volume-title":"Proc. ICML","author":"Nachmani"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414205"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413627"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10849"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022924"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268572"},{"key":"ref31","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref32","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"1","key":"ref34","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. ICLR","author":"Bahdanau"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"}],"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\/10446032.pdf?arnumber=10446032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:01:27Z","timestamp":1722574887000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446032","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}