{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:57:46Z","timestamp":1764403066376,"version":"3.28.0"},"reference-count":23,"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\/icassp39728.2021.9413739","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6733-6737","source":"Crossref","is-referenced-by-count":1,"title":["Improving Reconstruction Loss Based Speaker Embedding in Unsupervised and Semi-Supervised Scenarios"],"prefix":"10.1109","author":[{"given":"Jaejin","family":"Cho","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]},{"given":"Piotr","family":"Zelasko","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]},{"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"article-title":"But system description to voxceleb speaker recognition challenge 2019","year":"2019","author":"zeinali","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref13","first-page":"5265","article-title":"Cosface: Large margin cosine loss for deep face recognition","author":"wang","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"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":"Bayesian speaker verification with heavy-tailed priors","volume":"14","author":"kenny","year":"2010","journal-title":"Odyssey"},{"key":"ref17","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","year":"2020","author":"baevski","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2970"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054595"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"den oord","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3036"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"74","DOI":"10.21437\/Odyssey.2018-11","article-title":"Exploring the encoding layer and loss function in end-to-end speaker and language recognition system","author":"cai","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09413739.pdf?arnumber=9413739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:43Z","timestamp":1659485983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413739","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}