{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:39:06Z","timestamp":1776883146595,"version":"3.51.2"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016292","name":"National Applied Research Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016292","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832361","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"961-968","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget"],"prefix":"10.1109","author":[{"given":"Andy T.","family":"Liu","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Winkler","sequence":"additional","affiliation":[{"name":"ASUS Intelligent Cloud Services (AICS),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"issue":"03748","key":"ref5","article-title":"Representation learning with contrastive predictive coding","volume":"1807","author":"Oord","year":"2018","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1228"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389700"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2362"},{"issue":"07696","key":"ref19","article-title":"Sustainable self-supervised learning for speech representations","volume":"2406","author":"Lugo","year":"2024","journal-title":"CoRR"},{"issue":"15556","key":"ref20","article-title":"Training compute-optimal large language models","volume":"2203","author":"Hoffmann","year":"2022","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11112"},{"key":"ref23","article-title":"Parp: Prune, adjust and re-prune for self-supervised speech recognition","volume-title":"Proc. NeurIPS","author":"Jeff Lai"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095780"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10584"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747432"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023410"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414321"},{"key":"ref29","first-page":"201","article-title":"Why does unsupervised pre-training help deep learning?","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Erhan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1935"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747897"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-454"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-951"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1157"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-871"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832361.pdf?arnumber=10832361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:11:28Z","timestamp":1737101488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832361","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}