{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T20:27:22Z","timestamp":1770755242714,"version":"3.50.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"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":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3186162","type":"journal-article","created":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T19:39:18Z","timestamp":1656099558000},"page":"1357-1366","source":"Crossref","is-referenced-by-count":6,"title":["Ask2Mask: Guided Data Selection for Masked Speech Modeling"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9396-6319","authenticated-orcid":false,"given":"Murali Karthick","family":"Baskar","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Brno University of Technology, Brno-stred, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google. Inc., Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8049-2345","authenticated-orcid":false,"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google. Inc., Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9505-1833","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google. Inc., Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google. Inc., Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053799"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref5","first-page":"3","article-title":"Autoencoders, minimum description length, and Helmholtz free energy","volume-title":"Proc. 6th Int. Conf. Neural Inf. Process. Syst.","author":"Hinton","year":"1994"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref7","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref8","first-page":"1330","volume-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process.","author":"Hsu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-236"},{"key":"ref11","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1139"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1778"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-905"},{"key":"ref15","first-page":"1330","article-title":"PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1385"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3106197"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"issue":"33","key":"ref19","first-page":"21786","article-title":"Not all unlabeled data are equal: Learning to weight data in semi-supervised learning","author":"Ren","year":"2020","journal-title":"Proc. Conf. Neural Inf. Process. Syst."},{"key":"ref20","article-title":"Selection via proxy: Efficient data selection for deep learning","author":"Coleman","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414299"},{"key":"ref23","first-page":"1330","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref24","article-title":"PMI-masking: Principled masking of correlated spans","author":"Levine","year":"2020"},{"key":"ref25","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","first-page":"1330","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1758"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09806175.pdf?arnumber=9806175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:45:11Z","timestamp":1710387911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9806175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":31,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3186162","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}