{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:19:45Z","timestamp":1777130385010,"version":"3.51.4"},"reference-count":21,"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\/icassp43922.2022.9747325","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6132-6136","source":"Crossref","is-referenced-by-count":5,"title":["Self-Supervised Speaker Recognition Training using Human-Machine Dialogues"],"prefix":"10.1109","author":[{"given":"Metehan","family":"Cekic","sequence":"first","affiliation":[{"name":"University of California,Santa Barbara,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruirui","family":"Li","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeya","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Stolcke","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,Sunnyvale,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Upamanyu","family":"Madhow","sequence":"additional","affiliation":[{"name":"University of California,Santa Barbara,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"CoRR"},{"key":"ref14","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"ling","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref17","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc International Conference on Machine Learning"},{"key":"ref18","article-title":"Learning from noisy labels with deep neural networks","author":"sukhbaatar","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2699783"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371802"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054111"},{"key":"ref8","article-title":"DeCoAR 2.0: Deep contextualized acoustic representations with vector quantization","author":"ling","year":"2020","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"}],"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\/09747325.pdf?arnumber=9747325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:23Z","timestamp":1660594043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747325","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}