{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:20:08Z","timestamp":1772907608954,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687367","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Speaker Recognition Based on Pre-Trained Model and Deep Clustering"],"prefix":"10.1109","author":[{"given":"Liang","family":"He","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhida","family":"Song","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuanghong","family":"Liu","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengqi","family":"Niu","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Hu","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref3","volume":"abs\/2006.11477","author":"Baevski","year":"2020","journal-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app11156695"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/app12031478"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.03.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0166-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096659"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095433"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3267833"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446546"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/app12157463"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1558"},{"key":"ref23","first-page":"50221","article-title":"Disentangling voice and content with self-supervision for speaker recognition","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","author":"Ruder","year":"2017","journal-title":"An overview of multi-task learning in deep neural networks"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2614491"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2137"},{"key":"ref28","first-page":"3861","article-title":"Towards k-means-friendly spaces: Simultaneous deep learning and clustering","volume-title":"international conference on machine learning","author":"Yang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref31","author":"Snyder","year":"2015","journal-title":"Musan: A music, speech, and noise corpus"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414676"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"issue":"11","key":"ref34","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687367.pdf?arnumber=10687367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:31:00Z","timestamp":1727764260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687367","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}