{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T02:39:53Z","timestamp":1768531193314,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747162","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6142-6146","source":"Crossref","is-referenced-by-count":52,"title":["Self-Supervised Speaker Recognition with Loss-Gated Learning"],"prefix":"10.1109","author":[{"given":"Ruijie","family":"Tao","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Kong","family":"Aik Lee","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}]},{"given":"Rohan","family":"Kumar Das","sequence":"additional","affiliation":[{"name":"Fortemedia Singapore,Singapore"}]},{"given":"Ville","family":"Hautamaki","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref32","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"CoRR"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref35","first-page":"1641","article-title":"Semi-supervised contrastive learning with generalized contrastive loss and its application to speaker recognition","author":"inoue","year":"2020","journal-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref34","article-title":"The dku-dukeece system for the self-supervision speaker verification task of the 2021 voxceleb speaker recognition challenge","author":"cai","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"key":"ref12","first-page":"6829","article-title":"Disentangled speech embeddings using cross-modal selfsupervision","author":"nagrani","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414713"},{"key":"ref15","article-title":"The IDLAB VoxCeleb Speaker Recognition Challenge 2020 system description","author":"thienpondt","year":"2020"},{"key":"ref16","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref19","article-title":"Unsupervised representation learning for speaker recognition via contrastive equilibrium learning","author":"mun","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3125142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659567"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101058"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref2","first-page":"3317","article-title":"Joint application of speech and speaker recognition for automation and security in smart home","author":"lee","year":"2011","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3143036"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref21","article-title":"Augmentation adversarial training for unsupervised speaker recognition","author":"huh","year":"2020","journal-title":"Workshop on Self-Supervised Learning for Speech and Audio Processing NeurIPS"},{"key":"ref24","first-page":"1453","article-title":"Regularization via structural label smoothing","author":"li","year":"2020","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref23","article-title":"In defense of pseudo-labeling: An uncertainty-aware pseudolabel selection framework for semi-supervised learning","author":"rizve","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747162.pdf?arnumber=9747162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:41Z","timestamp":1660594001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747162","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}