{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:37:51Z","timestamp":1774539471371,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448455","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12141-12145","source":"Crossref","is-referenced-by-count":6,"title":["Self-Supervised Speaker Verification with Adaptive Threshold and Hierarchical Training"],"prefix":"10.1109","author":[{"given":"Zehua","family":"Zhou","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology,Department of Information and Communications Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Department of Information and Communications Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Department of Information and Communications Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3317","article-title":"Joint application of speech and speaker recognition for automation and security in smart home","volume-title":"Interspeech","author":"Lee"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659567"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3125142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414713"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-742"},{"key":"ref15","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"International Conference on Machine Learning (ICML)","author":"Arazo"},{"key":"ref16","first-page":"24392","article-title":"Understanding and improving early stopping for learning with noisy labels","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Bai"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11141"},{"key":"ref19","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Caron"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref25","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","article-title":"The idlab voxceleb speaker recognition challenge 2020 system description","author":"Thienpondt","year":"2020"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448455.pdf?arnumber=10448455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:08Z","timestamp":1722660848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448455\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448455","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}