{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T22:40:40Z","timestamp":1730241640841,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T00:00:00Z","timestamp":1706400000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T00:00:00Z","timestamp":1706400000000},"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":[[2024,1,28]]},"DOI":"10.1109\/iceic61013.2024.10457271","type":"proceedings-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T18:06:51Z","timestamp":1710871611000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["On the Disentanglement and Robustness of Self-Supervised Speech Representations"],"prefix":"10.1109","author":[{"given":"Yanjue","family":"Song","sequence":"first","affiliation":[{"name":"Ghent University - imec,IDLab,Ghent,Belgium"}]},{"given":"Doyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea"}]},{"given":"Nilesh","family":"Madhu","sequence":"additional","affiliation":[{"name":"Ghent University - imec,IDLab,Ghent,Belgium"}]},{"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref7","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2020","journal-title":"ICLR"},{"key":"ref8","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"journal-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref19","first-page":"27403","article-title":"The DARPA TIMIT acoustic-phonetic continuous speech corpus","volume":"93","author":"Garofolo","year":"1993","journal-title":"NASA STI\/Recon technical report n"},{"issue":"11","key":"ref20","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van","year":"2008","journal-title":"J. Mach. Learn. Res."},{"journal-title":"Noisy speech database for training speech enhancement algorithms and tts models","year":"2017","author":"Valentini-Botinhao","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.122712"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1612524113"}],"event":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","start":{"date-parts":[[2024,1,28]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2024,1,31]]}},"container-title":["2024 International Conference on Electronics, Information, and Communication (ICEIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10457047\/10457087\/10457271.pdf?arnumber=10457271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T19:13:47Z","timestamp":1711480427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10457271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,28]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iceic61013.2024.10457271","relation":{},"subject":[],"published":{"date-parts":[[2024,1,28]]}}}