{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:25:13Z","timestamp":1772119513680,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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 Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3345027","type":"journal-article","created":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:38:07Z","timestamp":1703014687000},"page":"144831-144843","source":"Crossref","is-referenced-by-count":5,"title":["SelfRemaster: Self-Supervised Speech Restoration for Historical Audio Resources"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6003-768X","authenticated-orcid":false,"given":"Takaaki","family":"Saeki","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-7847","authenticated-orcid":false,"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4385-7170","authenticated-orcid":false,"given":"Tomohiko","family":"Nakamura","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoko","family":"Tanji","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5617","authenticated-orcid":false,"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1942"},{"key":"ref3","first-page":"2819","article-title":"Crowdsourcing speech data for low-resource languages from low-income workers","volume-title":"Proc. LREC","author":"Abraham"},{"key":"ref4","first-page":"434","article-title":"CPJD corpus: Crowdsourced parallel speech corpus of Japanese dialects","volume-title":"Proc. LREC","author":"Takamichi"},{"key":"ref5","first-page":"2622","article-title":"Speech corpus of ainu folklore and end-to-end speech recognition for ainu language","volume-title":"Proc. LREC","author":"Matsuura"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746977"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-298"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref10","article-title":"Joint echo cancellation and noise suppression based on cascaded magnitude and complex mask estimation","author":"Shu","year":"2021","journal-title":"arXiv:2107.09298"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref12","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr\u00e1","year":"2022","journal-title":"arXiv:2206.03065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095557"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885934"},{"key":"ref16","article-title":"Audio super resolution using neural networks","author":"Kuleshov","year":"2017","journal-title":"arXiv:1708.00853"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2372342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553141"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.06.008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3042071"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414853"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref28","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv:2006.11477"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","author":"Chen","year":"2021","journal-title":"arXiv:2110.13900"},{"key":"ref31","article-title":"Applying Wav2vec2.0 to speech recognition in various low-resource languages","author":"Yi","year":"2020","journal-title":"arXiv:2012.12121"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1835"},{"key":"ref33","article-title":"Self-supervised learning for speech enhancement","author":"Wang","year":"2020","journal-title":"arXiv:2006.10388"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053925"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1496"},{"key":"ref36","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. ICLR","author":"Engel"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1121\/1.1912679"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168385"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.540325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2939"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref45","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv:2210.13438"},{"key":"ref46","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref48","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"arXiv:2010.05646"},{"key":"ref49","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"Wang","year":"2018","journal-title":"arXiv:1803.09017"},{"key":"ref50","first-page":"820","article-title":"Dual learning for machine translation","volume-title":"Proc. NIPS","author":"He"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref57","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","volume-title":"Proc. DCASE","author":"Mesaros"},{"key":"ref58","volume-title":"Tono no Mukashibanashi\/Sasaki Tokuo Hen","author":"Sasaki","year":"1985"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref62","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. ICML","author":"Ioffe"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10366219.pdf?arnumber=10366219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T00:08:00Z","timestamp":1705104480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10366219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3345027","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}