{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T21:13:08Z","timestamp":1781557988726,"version":"3.54.5"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889475","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":21,"title":["Leveraging Self-Supervised Learning for Speaker Diarization"],"prefix":"10.1109","author":[{"given":"Jiangyu","family":"Han","sequence":"first","affiliation":[{"name":"Brno University of Technology, Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Landini","sequence":"additional","affiliation":[{"name":"Brno University of Technology, Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johan","family":"Rohdin","sequence":"additional","affiliation":[{"name":"Brno University of Technology, Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Silnova","sequence":"additional","affiliation":[{"name":"Brno University of Technology, Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mireia","family":"Diez","sequence":"additional","affiliation":[{"name":"Brno University of Technology, Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luk\u00e1\u0161","family":"Burget","sequence":"additional","affiliation":[{"name":"Brno University of Technology, Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3422818"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-668"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3366756"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447817"},{"key":"ref19","article-title":"pyannote. audio speaker diarization pipeline at VoxSRC 2023","volume-title":"The VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23)","author":"Baroudi","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2462"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref23","first-page":"1","article-title":"The AMI meeting corpus","volume-title":"Proc. International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1788"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022775"},{"key":"ref30","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231926"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103104"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10451"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097049"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889475.pdf?arnumber=10889475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:14Z","timestamp":1774416254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889475\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889475","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}