{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:44:38Z","timestamp":1778694278247,"version":"3.51.4"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094711","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":18,"title":["Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech"],"prefix":"10.1109","author":[{"given":"Cheol Jun","family":"Cho","sequence":"first","affiliation":[{"name":"UC Berkeley,EECS,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wu","sequence":"additional","affiliation":[{"name":"UC Berkeley,EECS,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gopala K.","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"UC Berkeley,EECS,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.1016\/j.neuron.2018.04.031","article-title":"Encoding of articulatory kinematic trajectories in human speech sensorimotor cortex","volume":"98","author":"chartier","year":"2018","journal-title":"Neuron"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10892"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-316"},{"key":"ref21","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"ling","year":"2020"},{"key":"ref2","first-page":"1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"2020 decem","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref16","article-title":"fairseq s2t: Fast speech-to-text modeling with fairseq","author":"wang","year":"2020","journal-title":"Proceedings of the 2020 Conference of the Asian Chapter of the Association for Computational Linguistics (AACL) System Demonstrations"},{"key":"ref19","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022"},{"key":"ref18","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref8","article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","author":"shah","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414776"},{"key":"ref9","article-title":"Mocha: multichannel articulatory database","author":"wrench","year":"1999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref5","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"2021","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094711.pdf?arnumber=10094711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:58Z","timestamp":1700506858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094711","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}