{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T02:07:45Z","timestamp":1762999665320},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414310","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3885-3889","source":"Crossref","is-referenced-by-count":2,"title":["On Scaling Contrastive Representations for Low-Resource Speech Recognition"],"prefix":"10.1109","author":[{"given":"Lasse","family":"Borgholt","sequence":"first","affiliation":[{"name":"University of Copenhagen,Department of Computer Science,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tycho M. S.","family":"Tax","sequence":"additional","affiliation":[{"name":"University of Copenhagen,Department of Computer Science,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakob D.","family":"Havtorn","sequence":"additional","affiliation":[{"name":"Corti,Copenhagen,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Maaloe","sequence":"additional","affiliation":[{"name":"Corti,Copenhagen,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Igel","sequence":"additional","affiliation":[{"name":"University of Copenhagen,Department of Computer Science,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018","journal-title":"arXiv preprint 1807 03748"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1750"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref5","first-page":"3497","article-title":"Generative pretraining for speech with autoregressive predictive coding","author":"chung","year":"2020","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3084"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref2","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"arXiv preprint 1910 05453"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414310.pdf?arnumber=9414310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:30Z","timestamp":1659485970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414310","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}