{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:50:49Z","timestamp":1783140649302,"version":"3.54.6"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003343","name":"Cambridge Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003343","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096993","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Spectral Clustering-Aware Learning of Embeddings for Speaker Diarisation"],"prefix":"10.1109","author":[{"given":"Evonne P.C.","family":"Lee","sequence":"first","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref12","article-title":"Deep speaker verification model for low-resource languages and Vietnamese dataset","author":"thanh","year":"2021","journal-title":"Proc PACLIC"},{"key":"ref34","article-title":"Angular softmax for shortduration text-independent speaker verification","author":"huang","year":"2018","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383617"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref30","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413815"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","article-title":"Acoustic beamforming for speaker diarization of meetings","volume":"15","author":"anguera","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref17","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746952"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11368"},{"key":"ref22","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2006","journal-title":"Proc MLMI"},{"key":"ref21","author":"zhang","year":"2021","journal-title":"Beijing ZKJ-NPU speaker verification system for voxceleb speaker recognition challenge 2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.04.020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-566"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096993.pdf?arnumber=10096993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:16Z","timestamp":1699902016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096993","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}