{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T12:58:00Z","timestamp":1776171480341,"version":"3.50.1"},"reference-count":35,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Fulbright Junior Research Award granted by Polish-U.S. Fulbright Commission"},{"DOI":"10.13039\/501100001870","name":"Fundacja na rzecz Nauki Polskiej","doi-asserted-by":"publisher","award":["TEAM\/2017-3\/23"],"award-info":[{"award-number":["TEAM\/2017-3\/23"]}],"id":[{"id":"10.13039\/501100001870","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Centre, Poland","award":["2021\/42\/E\/ST7\/00452"],"award-info":[{"award-number":["2021\/42\/E\/ST7\/00452"]}]},{"name":"Excellence initiative – research university"}],"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.2024.3439993","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:55:14Z","timestamp":1723053314000},"page":"3960-3973","source":"Crossref","is-referenced-by-count":4,"title":["End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2413-077X","authenticated-orcid":false,"given":"Magdalena","family":"Rybicka","sequence":"first","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-8426","authenticated-orcid":false,"given":"Jes\u00fas","family":"Villalba","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8953-7872","authenticated-orcid":false,"given":"Thomas","family":"Thebaud","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-5753","authenticated-orcid":false,"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7834-6920","authenticated-orcid":false,"given":"Konrad","family":"Kowalczyk","sequence":"additional","affiliation":[{"name":"AGH University of Krakow, Krakow, Poland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383602"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref7","first-page":"667","article-title":"A deep analysis of speech separation guided diarization under realistic conditions","volume-title":"Proc. IEEE 2021 Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Fang","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095185"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1228"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746234"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-337"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414198"},{"key":"ref21","first-page":"1403","article-title":"Imputer: Sequence modelling via imputation and dynamic programming","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref24","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"Fujita","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687875"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10404"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11408"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094824"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363407"},{"key":"ref32","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref34","volume-title":"2000 NIST Speaker Recognition Evaluation LDC2001S97. Web Download","author":"Przybocki","year":"2001"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10629182.pdf?arnumber=10629182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T18:43:35Z","timestamp":1726253015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10629182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3439993","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}