{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:36:04Z","timestamp":1771979764238,"version":"3.50.1"},"reference-count":100,"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.2022.3195430","type":"journal-article","created":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:32:05Z","timestamp":1659659525000},"page":"1439-1453","source":"Crossref","is-referenced-by-count":13,"title":["Pretext Tasks Selection for Multitask Self-Supervised Audio Representation Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0788-3219","authenticated-orcid":false,"given":"Salah","family":"Zaiem","sequence":"first","affiliation":[{"name":"Télécom Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Titouan","family":"Parcollet","sequence":"additional","affiliation":[{"name":"LIA, Avignon Université, Avignon, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0028-327X","authenticated-orcid":false,"given":"Slim","family":"Essid","sequence":"additional","affiliation":[{"name":"Télécom Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelwahab","family":"Heba","sequence":"additional","affiliation":[{"name":"Université Paul Sabatier, IRIT, CNRS, Toulouse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref5","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grill","year":"2020"},{"key":"ref6","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.426"},{"key":"ref8","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref9","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-391"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"ref13","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-644"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2362"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2070"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3084"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref24","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Wang","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref26","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"CoRR","author":"Gidaris","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683426"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414405"},{"key":"ref29","article-title":"Learning speech representations from raw audio by joint audiovisual self-supervision","author":"Shukla","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1027"},{"key":"ref31","article-title":"Speechbrain","author":"Ravanelli"},{"key":"ref32","article-title":"Unsupervised cross-lingual representation learning for speech recognition","volume-title":"CoRR","author":"Conneau","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00815"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747197"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-556"},{"key":"ref39","first-page":"309","article-title":"Predicting what you already know helps: Provable self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2021"},{"key":"ref40","first-page":"9904","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Arora","year":"2019"},{"key":"ref41","article-title":"Theoretical analysis of self-training with deep networks on unlabeled data","volume-title":"CoRR","author":"Wei","year":"2020"},{"key":"ref42","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref43","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref44","article-title":"What should not be contrastive in contrastive learning","author":"Xiao","year":"2021"},{"key":"ref45","article-title":"On mutual information maximization for representation learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Tschannen","year":"2020"},{"key":"ref46","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian","year":"2020"},{"key":"ref47","volume-title":"Learning Representations by Maximizing Mutual Information Across Views","author":"Bachman","year":"2019"},{"key":"ref48","first-page":"15543","article-title":"Self-supervised learning with kernel dependence maximization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref49","article-title":"A mathematical exploration of why language models help solve downstream tasks","volume-title":"CoRR","author":"Saunshi","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01267"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2019-1943","article-title":"Joint speech recognition and speaker diarization via sequence transduction","volume-title":"CoRR","author":"Shafey","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1109\/WACV.2018.00092","article-title":"Learning image representations by completing damaged jigsaw puzzles","volume-title":"CoRR","author":"Kim","year":"2018"},{"key":"ref55","article-title":"Multiple pretext-task for self-supervised learning via mixing multiple image transformations","author":"Yamaguchi","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref57","first-page":"1157","article-title":"An introduction of variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res. Special Issue Variable Feature Selection"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref59","first-page":"1531","article-title":"Large scale multiple kernel learning","volume":"7","author":"Sonnenburg","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273594"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3123944"},{"key":"ref62","first-page":"1954","article-title":"Submodularity in data subset selection and active learning","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Wei","year":"2015"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-609","article-title":"Data-selective transfer learning for multi-domain speech recognition","author":"Doulaty","year":"2015"},{"key":"ref64","first-page":"585","article-title":"A kernel statistical test of independence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gretton","year":"2007"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430180"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00193"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25789-1_17"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-304"},{"key":"ref71","first-page":"1336","article-title":"Generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2990"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref74","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU51503.2021.9688028","article-title":"Kaizen: Continuously improving teacher using exponential moving average for semi-supervised speech recognition","author":"Manohar","year":"2021"},{"key":"ref75","article-title":"Large-scale ASR domain adaptation using self- and semi-supervised learning","author":"Hwang","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1857"},{"key":"ref77","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020"},{"key":"ref78","article-title":"Timit acoustic-phonetic continuous speech corpus","author":"Garofolo","year":"1992","journal-title":"Linguistic Data Consortium"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref80","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","volume-title":"Proc. 33rd Int. Conf. Int. Conf. Mach. Learn. -Volume 48","author":"Martins","year":"2016"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1121\/1.2208451"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225957"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/11520153_9"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"issue":"1","key":"ref85","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach. Learn."},{"key":"ref86","article-title":"VQ-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref88","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-236","article-title":"Robust wav2vec 2.0: Analyzing domain shift in self-supervised pre-training","author":"Hsu","year":"2021"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969559"},{"key":"ref90","article-title":"Classification automatique des signaux audio-frquences: Reconnaissance des instruments de musique","author":"Essid","year":"2005"},{"key":"ref91","first-page":"441","article-title":"Yaafe, an easy to use and efficient audio feature extraction software","volume-title":"Proc. 11th Int. Soc. Music Inf. Retrieval Conf.","author":"Mathieu","year":"2010"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404779"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1780"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09846981.pdf?arnumber=9846981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T08:37:45Z","timestamp":1706776665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9846981\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":100,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3195430","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}