{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:41:52Z","timestamp":1730230912442,"version":"3.28.0"},"reference-count":24,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447345","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12061-12065","source":"Crossref","is-referenced-by-count":0,"title":["Self-Supervised Models of Speech Infer Universal Articulatory Kinematics"],"prefix":"10.1109","author":[{"given":"Cheol Jun","family":"Cho","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Rembrand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan W","family":"Black","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gopala K.","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","year":"2021","author":"Shah","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094711"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096796"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1159\/000261913"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.4812765"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11233"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10892"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5334\/labphon.237"},{"key":"ref12","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":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Pratap","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097097"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-316"},{"article-title":"Mocha: multichannel articulatory database","year":"1999","author":"Wrench","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.4987629"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706629"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-485"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-023-01468-4"}],"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\/10447345.pdf?arnumber=10447345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:36:16Z","timestamp":1722576976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447345","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}