{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T05:40:34Z","timestamp":1770702034373,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icassp39728.2021.9414841","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7183-7187","source":"Crossref","is-referenced-by-count":18,"title":["End-To-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings"],"prefix":"10.1109","author":[{"given":"Soumi","family":"Maiti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hakan","family":"Erdogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Wisdom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"pyannote.audio: neural building blocks for speaker diarization","author":"bredin","year":"2019"},{"key":"ref30","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","volume":"2","author":"clevert","year":"2016","journal-title":"arXiv preprint arXiv 1511 07289"},{"key":"ref10","first-page":"217","article-title":"A study of the cosine distance-based mean shift for telephone speech diarization","volume":"22","author":"senoussaoui","year":"2013","journal-title":"IEEE\/ACM TASLP"},{"key":"ref11","first-page":"788","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE\/ACM TASLP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref29","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"arXiv preprint arXiv 2006 16236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1007\/11965152_19","article-title":"Overlap in meetings: Asr effects and analysis by dialog factors, speakers, and collection site","author":"\u00e7etin","year":"2006","journal-title":"Proc Int’l Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref21","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"fujita","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref24","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"fujita","year":"2020","journal-title":"arXiv preprint arXiv 2003 07516"},{"key":"ref23","article-title":"Speaker diarization using an end-to-end model","author":"wang","year":"2019","journal-title":"Google Patents"},{"key":"ref26","article-title":"Discriminative neural clustering for speaker diarisation","author":"li","year":"2019","journal-title":"arXiv preprint arXiv 1910 01500"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"}],"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\/09414841.pdf?arnumber=9414841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:52Z","timestamp":1652197252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414841","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}