{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T21:32:55Z","timestamp":1781818375687,"version":"3.54.5"},"reference-count":33,"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\/icassp39728.2021.9413832","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5824-5828","source":"Crossref","is-referenced-by-count":40,"title":["Microsoft Speaker Diarization System for the Voxceleb Speaker Recognition Challenge 2020"],"prefix":"10.1109","author":[{"given":"Xiong","family":"Xiao","sequence":"first","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902870"},{"key":"ref31","article-title":"ResNeXt and Res2Net structure for speaker verification","author":"zhou","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref10","article-title":"LIUM SpkDiarization: an open source toolkit for diarization","author":"meignier","year":"2010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref12","first-page":"4930","article-title":"Speaker diarization using deep neural network embeddings","author":"garcia-romero","year":"2017","journal-title":"ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref14","article-title":"First DIHARD challenge evaluation plan","author":"ryant","year":"2018","journal-title":"Technical report 2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-91","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: Insights for automatic speech recognition","author":"\u00e7etin","year":"2006","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/CHiME.2020-1","article-title":"CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref28","article-title":"Continuous speech separation with conformer","author":"chen","year":"2020"},{"key":"ref4","first-page":"788","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Trans on ASLP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref3","article-title":"The STC system for the chime-6 challenge","author":"medennikov","year":"2020","journal-title":"CHiME 2020 Workshop"},{"key":"ref6","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"ICASSP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003826"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054176"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-3015","article-title":"Conformer: Convolution-augmented transformer for speech recognition","author":"gulati","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004031"}],"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\/09413832.pdf?arnumber=9413832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:23:54Z","timestamp":1672129434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413832","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}