{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:01:31Z","timestamp":1777734091051,"version":"3.51.4"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688178","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"702-709","source":"Crossref","is-referenced-by-count":7,"title":["Dive: End-to-End Speech Diarization Via Iterative Speaker Embedding"],"prefix":"10.1109","author":[{"given":"Neil","family":"Zeghidour","sequence":"first","affiliation":[{"name":"Google Research,Brain Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Teboul","sequence":"additional","affiliation":[{"name":"Google Research,Brain Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Grangier","sequence":"additional","affiliation":[{"name":"Google Research,Brain Team"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"pyannote.metrics: a toolkit for re-producible evaluation, diagnostic, and error analysis of speaker diarization systems","author":"bredin","year":"2017","journal-title":"INTERSPEECH 2017 - 18th Annual Conference of the International Speech Communication Association"},{"key":"ref38","article-title":"End-to-end speaker diarization as post-processing","author":"horiguchi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2418"},{"key":"ref31","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"SSW"},{"key":"ref30","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics AISTATS 2011"},{"key":"ref37","author":"snyder","year":"2015","journal-title":"MUSAN A Music Speech and Noise Corpus"},{"key":"ref36","author":"cieri","year":"2005","journal-title":"Fisher english training speech part 1"},{"key":"ref35","author":"cieri","year":"2004","journal-title":"Fisher english training speech part 1"},{"key":"ref34","article-title":"Sequence to multi-sequence learning via conditional chain mapping for mixture signals","author":"shi","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLR (Poster)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref13","article-title":"Integrating end-to-end neural and clustering-based diarization: Getting the best of both worlds","volume":"abs 2010 13366","author":"kinoshita","year":"2020","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383617"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178822"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref19","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"fujita","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-566"},{"key":"ref27","year":"2000","journal-title":"2000 speaker recognition evaluation plan"},{"key":"ref3","article-title":"A review of speaker diarization: Recent advances with deep learning","volume":"abs 2101 9624","author":"park","year":"2021","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref29","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref8","first-page":"2739","article-title":"Developing online speaker diarization system","author":"dimitriadis","year":"2017","journal-title":"INTERSPEECH 2017 - 18th Annual Conference of the International Speech Communication Association"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","article-title":"Speaker diarization: A review of recent research","volume":"20","author":"mir\u00f3","year":"2012","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7951789"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref42","article-title":"The third DIHARD diarization challenge","volume":"abs 2012 1477","author":"ryant","year":"2020","journal-title":"CoRR"},{"key":"ref24","article-title":"Wavesplit: End-to-end speech separation by speaker clustering","author":"zeghidour","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383523"},{"key":"ref26","article-title":"Neural speaker diarization with speaker-wise chain rule","volume":"abs 2006 1796","author":"fujita","year":"2020","journal-title":"CoRR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688178.pdf?arnumber=9688178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:41:24Z","timestamp":1652719284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688178","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}