{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:33Z","timestamp":1775229993027,"version":"3.50.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3389636","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:28:20Z","timestamp":1713288500000},"page":"2391-2406","source":"Crossref","is-referenced-by-count":25,"title":["Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5063-0508","authenticated-orcid":false,"given":"Daisuke","family":"Niizumi","sequence":"first","affiliation":[{"name":"Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}]},{"given":"Daiki","family":"Takeuchi","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7856-248X","authenticated-orcid":false,"given":"Yasunori","family":"Ohishi","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1759-4533","authenticated-orcid":false,"given":"Noboru","family":"Harada","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}]},{"given":"Kunio","family":"Kashino","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref7","article-title":"Are large-scale datasets necessary for self-supervised pre-training?","author":"El-Nouby","year":"2021"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref13","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref16","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","volume-title":"Proc. HEAR: Holistic Eval. Audio Representations (NeurIPS 2021 Competition)","volume":"166","author":"Niizumi","year":"2022"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref18","first-page":"1298","article-title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221007"},{"key":"ref21","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic Tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094795"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096318"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00999"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-221"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-822"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096793"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746220"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095480"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10126"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746790"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3202093"},{"key":"ref42","article-title":"Training one model to detect heart and lung sound events from single point auscultations","author":"Melms","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747348"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.118"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.insights-1.9"},{"key":"ref47","article-title":"Self-Distillation for further pre-training of transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref52","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref56","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engel","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768246"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref59","article-title":"How to fine-tune vision models with SGD","author":"Kumar","year":"2022"},{"key":"ref60","article-title":"Voxforge","author":"MacLean","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2478068"},{"key":"ref62","article-title":"The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use","author":"Sturm","year":"2013"},{"key":"ref63","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref64","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909674"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref67","article-title":"End-to-end audio strikes back: Boosting augmentations towards an efficient audio classification network","author":"Gazneli","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022991"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ab03ea"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248130"},{"key":"ref74","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref76","first-page":"439","article-title":"Accumulated gradient normalization","volume-title":"Proc. Asian Conf. Mach. Learn.","volume":"77","author":"Hermans","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1426"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2022.3204910"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_28"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10502167.pdf?arnumber=10502167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:59:44Z","timestamp":1714762784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10502167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3389636","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}