{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:08:51Z","timestamp":1776881331622,"version":"3.51.2"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383523","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"841-848","source":"Crossref","is-referenced-by-count":26,"title":["Online End-To-End Neural Diarization with Speaker-Tracing Buffer"],"prefix":"10.1109","author":[{"given":"Yawen","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shota","family":"Horiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Nagamatsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404842"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1891"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004029"},{"key":"ref31","article-title":"Corpus of Spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-18"},{"key":"ref37","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref34","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-638","article-title":"GMM-UBM based open-set online speaker diarization","author":"geiger","year":"2010","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-149","article-title":"Improved novelty detection for online gmm based speaker diarization","author":"markov","year":"2008","journal-title":"InterSpeech"},{"key":"ref14","first-page":"3105","article-title":"Integrating online i-vector extractor with information bottleneck based speaker diarization system","author":"madikeri","year":"2015","journal-title":"InterSpeech"},{"key":"ref15","first-page":"4930","article-title":"Speaker diarization using deep neural network embeddings","author":"garcia-romero","year":"2017","journal-title":"ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472638"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref18","first-page":"4879","article-title":"Generalized end-to-end loss for speaker verification","author":"wan","year":"2018","journal-title":"ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref28","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"fujita","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0355"},{"key":"ref27","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"fujita","year":"2020"},{"key":"ref3","article-title":"2000 NIST Speaker Recognition Evaluation","year":"0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053122"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461546"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2739","DOI":"10.21437\/Interspeech.2017-166","article-title":"Developing online speaker diarization system","author":"dimitriadis","year":"2017","journal-title":"InterSpeech"},{"key":"ref21","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053477"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383523.pdf?arnumber=9383523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:21Z","timestamp":1671714981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383523","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}