{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:01:28Z","timestamp":1777734088569,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413436","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"7188-7192","source":"Crossref","is-referenced-by-count":29,"title":["End-To-End Speaker Diarization as Post-Processing"],"prefix":"10.1109","author":[{"given":"Shota","family":"Horiguchi","sequence":"first","affiliation":[{"name":"Research & Development Group,Hitachi, Ltd,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"Research & Development Group,Hitachi, Ltd,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Nagamatsu","sequence":"additional","affiliation":[{"name":"Research & Development Group,Hitachi, Ltd,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054251"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-21"},{"key":"ref16","article-title":"BUT system description for DIHARD Speech Diarization Challenge 2019","author":"landini","year":"2019","journal-title":"arXiv 1910 08847"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2813"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref7","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"fujita","year":"2020","journal-title":"arXiv 2003 02966"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref9","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"fujita","year":"2020","journal-title":"arXiv 2006 01796"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref20","first-page":"381","article-title":"Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system","author":"kinoshita","year":"2020","journal-title":"ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref25","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"arXiv 1510 08484 [cs]"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413436.pdf?arnumber=9413436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:20:08Z","timestamp":1659471608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413436","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}