{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:22Z","timestamp":1775230042846,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/asru51503.2021.9687875","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"98-105","source":"Crossref","is-referenced-by-count":30,"title":["Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors"],"prefix":"10.1109","author":[{"given":"Shota","family":"Horiguchi","sequence":"first","affiliation":[{"name":"Hitachi, Ltd.,Japan"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,USA"}]},{"given":"Yawen","family":"Xue","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Japan"}]},{"given":"Yuki","family":"Takashima","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Japan"}]},{"given":"Yohei","family":"Kawaguchi","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Japan"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383617"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413436"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054577"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3233\/FI-2013-883"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref1","article-title":"A review of speaker diarization: Recent advances with deep learning","author":"park","year":"2021","journal-title":"ArXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00940"},{"key":"ref21","article-title":"Semantic instance segmentation via deep metric learning","author":"fathi","year":"2017","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref25","first-page":"577","article-title":"Constrained k-means clustering with background knowledge","author":"wagstaff","year":"0","journal-title":"ICML"},{"key":"ref50","article-title":"The Hitachi-JHU DIHARD III system: Competitive end-to-end neural diarization and x-vector clustering systems combined by DOVER-Lap","author":"horiguchi","year":"0","journal-title":"DIHARD III"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383555"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414841"},{"key":"ref13","first-page":"7193","article-title":"BW-ED A-EEND: Streaming end-to-end neural speaker diarization for a variable number of speakers","author":"han","year":"0","journal-title":"ICASSP"},{"key":"ref14","article-title":"Encoder-decoder based attractor calculation for end-to-end neural diarization","author":"horiguchi","year":"2021","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1909"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref7","year":"0","journal-title":"The 2000 NIST Speaker Recognition Evaluation"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054251"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLRE"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1550"},{"key":"ref48","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"fujita","year":"2020","journal-title":"ArXiv"},{"key":"ref47","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NeurIPS"},{"key":"ref42","first-page":"7164","article-title":"Voice separation with an unknown number of multiple speakers","author":"nachmani","year":"0","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"}],"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\/09687875.pdf?arnumber=9687875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:27Z","timestamp":1652201907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687875\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687875","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}