{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T18:56:10Z","timestamp":1783191370896,"version":"3.54.6"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023410","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"115-122","source":"Crossref","is-referenced-by-count":4,"title":["Match to Win: Analysing Sequences Lengths for Efficient Self-Supervised Learning in Speech and Audio"],"prefix":"10.1109","author":[{"given":"Yan","family":"Gaol","sequence":"first","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Fernandez-Marques","sequence":"additional","affiliation":[{"name":"Samsung AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Titouan","family":"Parcollet","sequence":"additional","affiliation":[{"name":"Avignon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro P. B.","family":"de Gusmao","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas D.","family":"Lane","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1566"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref7","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10644"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref12","article-title":"Fithubert: Going thin-ner and deeper for knowledge distillation of speech self-supervised learning","author":"Lee","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"21256","article-title":"Parp: Prune, adjust and re-prune for self-supervised speech recognition","volume":"34","author":"Lai","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Speechbrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"Warden","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref19","article-title":"Timers and such: A practical benchmark for spoken language understanding with numbers","author":"Lugosch","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref23","article-title":"Mixed precision training","volume-title":"International Conference on Learning Representations","author":"Micikevicius"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023410.pdf?arnumber=10023410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:41:08Z","timestamp":1707813668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023410","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}