{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:39Z","timestamp":1781713179705,"version":"3.54.5"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3233237","type":"journal-article","created":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T18:59:23Z","timestamp":1672426763000},"page":"706-720","source":"Crossref","is-referenced-by-count":22,"title":["Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3166-4956","authenticated-orcid":false,"given":"Shota","family":"Horiguchi","sequence":"first","affiliation":[{"name":"Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7449-5726","authenticated-orcid":false,"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8489-9487","authenticated-orcid":false,"given":"Yuki","family":"Takashima","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2329-5441","authenticated-orcid":false,"given":"Yohei","family":"Kawaguchi","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2081790"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018\u20133047"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538680"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178882"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414841"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1909"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688178"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413436"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383523"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-708"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-750"},{"key":"ref29","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383555"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687875"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746234"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-941"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688271"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-149"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747772"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2023.3279781"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095185"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-991"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-384"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053477"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688044"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054577"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"issue":"11","key":"ref57","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref58","article-title":"Semantic instance segmentation via deep metric learning","author":"Fathi"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00940"},{"key":"ref60","first-page":"577","article-title":"Constrained k-means clustering with background knowledge","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Wagstaff","year":"2001"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3233\/FI-2013-883"},{"key":"ref62","article-title":"2000 NIST speaker recognition evaluation"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref65","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref67","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref69","article-title":"The Hitachi-JHU DIHARD III system: Competitive end-to-end neural diarization and x-vector clustering systems combined by DOVER-Lap","volume-title":"Proc. 3rd DIHARD Speech Diarization Challenge Workshop","author":"Horiguchi","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-23"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10363"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1021\/ac60214a047"},{"key":"ref73","article-title":"BUT system description for the third DIHARD speech diarization challenge","volume-title":"Proc. 3rd DIHARD Speech Diarization Challenge Workshop","author":"Landini","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10003998.pdf?arnumber=10003998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T04:25:18Z","timestamp":1707452718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10003998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3233237","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}