{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T22:09:15Z","timestamp":1755036555219,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447489","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10901-10905","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging in-the-wild Data for Effective Self-supervised Pretraining in Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Wang","sequence":"first","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qibing","family":"Bai","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Han","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen (CUHK-Shenzhen),China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","year":"2021","author":"Wang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094795"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096659"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"article-title":"Self-supervised curriculum learning for speaker verification","year":"2022","author":"Heo","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-453"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200915"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10192957"},{"key":"ref28","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447489.pdf?arnumber=10447489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:42:57Z","timestamp":1722577377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447489","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}