{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:01:18Z","timestamp":1772172078637,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.2985586","type":"journal-article","created":{"date-parts":[[2020,4,8]],"date-time":"2020-04-08T16:57:52Z","timestamp":1586365072000},"page":"600-604","source":"Crossref","is-referenced-by-count":33,"title":["Pre-Training Audio Representations With Self-Supervision"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7682-6795","authenticated-orcid":false,"given":"Marco","family":"Tagliasacchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beat","family":"Gfeller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"de Chaumont Quitry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominik","family":"Roblek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref33","article-title":"Spoken language identification","author":"oponowicz","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref30","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"zhai","year":"2019"},{"key":"ref37","first-page":"9","article-title":"Detection and classification of acoustic scenes and events","author":"mesaros","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13103"},{"key":"ref35","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume":"70","author":"engel","year":"0","journal-title":"Proc 34th Int'l Conf on Machine Learning (ICML'17)"},{"key":"ref34","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref10","article-title":"Unsupervised feature learning for audio analysis","author":"meyer","year":"0","journal-title":"Proc Workshop Track"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref28","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref4","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref6","first-page":"7365","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","author":"chung","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2194"},{"key":"ref2","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00840"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.638"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1083-5"},{"key":"ref23","first-page":"7354","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","author":"chung","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09060816.pdf?arnumber=9060816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:56:42Z","timestamp":1641988602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9060816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.2985586","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}