{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:30:15Z","timestamp":1774128615170,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096925","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Self-Supervised Audio-Visual Speaker Representation with Co-Meta Learning"],"prefix":"10.1109","author":[{"given":"Hui","family":"Chen","sequence":"first","affiliation":[{"name":"Tianjin University,Tianjin International Engineering Institute,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref12","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"},{"key":"ref15","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","author":"yu","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162078"},{"key":"ref11","author":"thienpondt","year":"2020","journal-title":"The idlab voxceleb speaker recognition challenge 2020 system description"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414713"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3091932"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref16","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007515423169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref23","author":"snyder","year":"2015","journal-title":"MUSAN A Music Speech and Noise Corpus"},{"key":"ref26","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3468.618255"},{"key":"ref22","author":"nagrani","year":"2017","journal-title":"Voxceleb a large-scale speaker identification dataset"},{"key":"ref21","author":"chung","year":"2018","journal-title":"VoxCeleb2 Deep speaker recognition"},{"key":"ref28","author":"cho","year":"2021","journal-title":"The jhu submission to voxsrc-21 Track 3"},{"key":"ref27","author":"han","year":"2022","journal-title":"Self-supervised speaker verification using dynamic loss-gate and label correction"},{"key":"ref29","author":"mun","year":"0","journal-title":"Snuhil system for the voxceleb speaker recognition challenge 2021"},{"key":"ref8","author":"stafylakis","year":"2019","journal-title":"Self-supervised speaker embeddings"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref4","author":"safari","year":"2020","journal-title":"Self-attention encoding and pooling for speaker recognition"},{"key":"ref3","author":"desplanques","year":"2020","journal-title":"Ecapatdnn Emphasized channel attention propagation and aggregation in tdnn based speaker verification"},{"key":"ref6","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"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096925.pdf?arnumber=10096925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:40Z","timestamp":1700507140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096925","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}