{"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":1776441824131,"version":"3.51.2"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747526","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6127-6131","source":"Crossref","is-referenced-by-count":27,"title":["Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization"],"prefix":"10.1109","author":[{"given":"Mufan","family":"Sang","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,TX,USA"}]},{"given":"Haoqi","family":"Li","sequence":"additional","affiliation":[{"name":"Amazon AWS AI,USA"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon AWS AI,USA"}]},{"given":"Andrew O.","family":"Arnold","sequence":"additional","affiliation":[{"name":"Amazon AWS AI,USA"}]},{"given":"Li","family":"Wan","sequence":"additional","affiliation":[{"name":"Amazon AWS AI,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2868"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413403"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref17","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":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref18","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":"ref19","first-page":"6829","article-title":"Disentangled speech embeddings using crossmodal self-supervision","author":"nagrani","year":"2020","journal-title":"ICASSP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref4","first-page":"4879","article-title":"Generalized end-to-end loss for speaker verification","author":"wan","year":"2018","journal-title":"ICASSP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref6","first-page":"5265","article-title":"Cosface: Large margin cosine loss for deep face recognition","author":"wang","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref22","article-title":"Learning speaker embedding with momentum contrast","author":"ding","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref24","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":"Proc Interspeech 2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref26","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"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\/09747526.pdf?arnumber=9747526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:52Z","timestamp":1660594012000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747526","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}