{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:14:12Z","timestamp":1776888852963,"version":"3.51.2"},"reference-count":31,"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\/icassp43922.2022.9747594","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"7647-7651","source":"Crossref","is-referenced-by-count":17,"title":["RawNeXt: Speaker Verification System For Variable-Duration Utterances With Deep Layer Aggregation And Extended Dynamic Scaling Policies"],"prefix":"10.1109","author":[{"given":"Ju-Ho","family":"Kim","sequence":"first","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Hye-Jin","family":"Shim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Jungwoo","family":"Heo","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1354"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref16","article-title":"Voxsrc 2020: The second voxceleb speaker recognition challenge","author":"nagrani","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref28","first-page":"7","article-title":"On the convergence of adam and beyond","volume":"5","author":"sashank","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.21437\/Interspeech.2017-1608","article-title":"End-to-end text-independent speaker verification with triplet loss on short utterances","author":"zhang","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2240"},{"key":"ref29","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004029"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1489"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref20","first-page":"286","article-title":"Supervised attention for speaker recognition","author":"kye","year":"2021","journal-title":"2021 IEEE Spoken Language Technology Workshop (SLT)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1283"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3044446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682712"},{"key":"ref26","article-title":"The xx205 system for the voxceleb speaker recognition challenge 2020","author":"xiang","year":"2020"},{"key":"ref25","article-title":"The idlab voxceleb speaker recognition challenge 2020 system description","author":"thienpondt","year":"2020"}],"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\/09747594.pdf?arnumber=9747594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:06:12Z","timestamp":1660579572000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747594","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}