{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:49:01Z","timestamp":1782834541630,"version":"3.54.5"},"reference-count":66,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100005825","name":"National Institute of Food and Agriculture","doi-asserted-by":"publisher","award":["#2020-67021-32799"],"award-info":[{"award-number":["#2020-67021-32799"]}],"id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]}],"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.2022.3200911","type":"journal-article","created":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T19:57:32Z","timestamp":1661198252000},"page":"1329-1341","source":"Crossref","is-referenced-by-count":47,"title":["RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1047-1338","authenticated-orcid":false,"given":"Efthymios","family":"Tzinis","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2237-3898","authenticated-orcid":false,"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem, Jerusalem, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vamsi K.","family":"Ithapu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3027-7567","authenticated-orcid":false,"given":"Buye","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paris","family":"Smaragdis","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Speech Enhancement","author":"Benesty","year":"2006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2986896"},{"key":"ref5","article-title":"Phase-aware speech enhancement with deep complex u-net","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choi","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870725"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462155"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref14","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688176"},{"key":"ref17","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1519"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053925"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1868"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937250"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746973"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413431"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937218"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907015"},{"key":"ref28","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"Proc. Adv. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Wisdom","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616166"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632783"},{"key":"ref31","article-title":"Training speech enhancement systems with noisy speech datasets","author":"Saito","year":"2021"},{"key":"ref32","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682695"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1243"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632771"},{"key":"ref37","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"Xie","year":"2020","journal-title":"Proc. Adv. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref38","article-title":"Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Berthelot","year":"2019"},{"key":"ref39","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Sohn","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413723"},{"key":"ref41","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Int. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-571"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1827"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054172"},{"key":"ref49","article-title":"The central limit theorem for weakly dependent random variables by the moment method","author":"Fleermann","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref53","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Jort","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"},{"key":"ref56","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414322"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-021-01683-x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"Diederik Kingma","year":"2014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09864253.pdf?arnumber=9864253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:42:35Z","timestamp":1706791355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9864253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":66,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3200911","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}