{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:02:56Z","timestamp":1761238976316,"version":"3.28.0"},"reference-count":23,"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\/icassp43922.2022.9747209","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7637-7641","source":"Crossref","is-referenced-by-count":2,"title":["Robust Speaker Verification with Joint Self-Supervised and Supervised Learning"],"prefix":"10.1109","author":[{"given":"Kai","family":"Wang","sequence":"first","affiliation":[{"name":"Samsung R&D Institute China Xian"}]},{"given":"Xiaolei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute China Xian"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute China Xian"}]},{"given":"Yuguang","family":"Li","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute China Xian"}]},{"given":"Jaeyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Advanced Institute of Technology"}]},{"given":"Kiho","family":"Cho","sequence":"additional","affiliation":[{"name":"Samsung Advanced Institute of Technology"}]},{"given":"Sung-UN","family":"Park","sequence":"additional","affiliation":[{"name":"Samsung Advanced Institute of Technology"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-excitation networks","volume":"42","author":"hu","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/SIU49456.2020.9302162"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP40776.2020.9053373"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/SLT48900.2021.9383580"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TASLP.2019.2915167"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV.2017.167"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2019-2663"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref18","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"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICSDA.2017.8384449"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Interspeech.2017-1608"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.21437\/Interspeech.2019-2357"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2019-2842"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TASLP.2019.2921890"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2018-993"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref1","first-page":"5329","article-title":"X-vectors: Robust dnn embeddings for speaker recognition","author":"jones","year":"2018","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.21437\/Interspeech.2020-1064"},{"year":"0","article-title":"Zeroth korean","key":"ref20"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: Audio and music signal analysis in python","author":"mcfee","year":"2015"},{"key":"ref23","first-page":"2579","article-title":"Visualizing data using t-sne","author":"hinton","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747209.pdf?arnumber=9747209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:17Z","timestamp":1660594217000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747209","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}