{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:46:29Z","timestamp":1776887189942,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414057","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6149-6153","source":"Crossref","is-referenced-by-count":16,"title":["Graph Attention Networks for Speaker Verification"],"prefix":"10.1109","author":[{"given":"Jee-weon","family":"Jung","sequence":"first","affiliation":[{"name":"University of Seoul,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hee-Soo","family":"Heo","sequence":"additional","affiliation":[{"name":"Naver Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Naver Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref32","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","author":"chen","year":"2020","journal-title":"Proc ICML"},{"key":"ref31","first-page":"2485","article-title":"Column networks for collective classification","author":"pham","year":"2017","journal-title":"Proc AAAI"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472722"},{"key":"ref35","article-title":"SGDR: Stochastic Gradient Descent with Warm Restarts","author":"loshchilov","year":"2017","journal-title":"Proc ICLR"},{"key":"ref34","article-title":"NSML: A Machine Learning Platform That Enables You to Focus on Your Models","author":"sung","year":"2017","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref11","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref14","article-title":"Discriminative and generative approaches for long- and short-term speaker characteristics modeling application to speaker verification","author":"dehak","year":"2010","journal-title":"Ph D thesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853880"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054176"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947437"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462575"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947442"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref2","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":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref22","article-title":"GRAPH ATTENTION NETWORKS","author":"velickovic","year":"2018","journal-title":"Proc ICLR"},{"key":"ref21","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"Identity mappings in deep residual networks","volume":"9908","author":"he","year":"2016","journal-title":"Lecture Notes in Computer Science"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref26","article-title":"Clova baseline system for the voxceleb speaker recognition challenge 2020","author":"heo","year":"2020"},{"key":"ref25","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"NIPS"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414057.pdf?arnumber=9414057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:31Z","timestamp":1659485971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414057","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}