{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:55Z","timestamp":1775200015377,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434721","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data"],"prefix":"10.1109","author":[{"given":"Sara","family":"Barahona","sequence":"first","affiliation":[{"name":"Universidad Autónoma de Madrid,AUDIAS Research Group,Madrid,Spain"}]},{"given":"Ladislav","family":"Mo\u0161nery","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}]},{"given":"Themos","family":"Stafylakisz","sequence":"additional","affiliation":[{"name":"Athens University of Economics and Business | Omilia | Archimedes\/Athena R.C,Greece"}]},{"given":"Old\u0159ich","family":"Plchoty","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}]},{"given":"Junyi","family":"Pengy","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}]},{"given":"Luk\u00e1\u0161","family":"Burgety","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}]},{"given":"Jan","family":"\u010cernocky\u00fd","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp34228.2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","first-page":"12 449","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022775"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-486"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3331949"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1232"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103104"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1232"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref25","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2017","journal-title":"arXiv 1607.08022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434721.pdf?arnumber=11434721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:42Z","timestamp":1775192322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434721","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}