{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:03:44Z","timestamp":1776441824184,"version":"3.51.2"},"reference-count":24,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096915","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":21,"title":["Pushing the Limits of Self-Supervised Speaker Verification using Regularized Distillation Framework"],"prefix":"10.1109","author":[{"given":"Yafeng","family":"Chen","sequence":"first","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luyao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","volume":"abs 1807 3748","author":"van den oord","year":"2018","journal-title":"CoRR"},{"key":"ref24","article-title":"Unsupervised representation learning for speaker recognition via contrastive equilibrium learning","volume":"abs 2010 11433","author":"mun","year":"2020","journal-title":"CoRR"},{"key":"ref12","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"119","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref23","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-289"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref22","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":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1442"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10278"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414713"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref16","article-title":"Bootstrap your own latent - A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","article-title":"Vicreg: Variance-invariance-covariance regularization for selfsupervised learning","author":"bardes","year":"2022","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-742"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747526"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1440"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref3","author":"cho","year":"2021","journal-title":"The jhu submission to voxsrc-21 Track 3"},{"key":"ref6","author":"heo","year":"2022","journal-title":"Self-supervised curriculum learning for speaker verification"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-126"}],"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\/10096915.pdf?arnumber=10096915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:00:23Z","timestamp":1700488823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096915","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}