{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T17:00:26Z","timestamp":1781370026307,"version":"3.54.1"},"reference-count":55,"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\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP21H00906"],"award-info":[{"award-number":["JP21H00906"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"PRESTO, Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJPR23I7"],"award-info":[{"award-number":["JPMJPR23I7"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3374874","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T19:21:49Z","timestamp":1709839309000},"page":"36990-36999","source":"Crossref","is-referenced-by-count":14,"title":["Dysarthric Speech Recognition Using Pseudo-Labeling, Self-Supervised Feature Learning, and a Joint Multi-Task Learning Approach"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9808-0250","authenticated-orcid":false,"given":"Ryoichi","family":"Takashima","sequence":"first","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuya","family":"Sawa","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6492-3754","authenticated-orcid":false,"given":"Ryo","family":"Aihara","sequence":"additional","affiliation":[{"name":"Information Technology Research and Development Center, Mitsubishi Electric Corporation, Kamakura, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5005-7679","authenticated-orcid":false,"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshie","family":"Imai","sequence":"additional","affiliation":[{"name":"Information Technology Research and Development Center, Mitsubishi Electric Corporation, Kamakura, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref3","volume-title":"Cerebral Palsy: Hope Through Research","year":"2009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462290"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1751"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref9","first-page":"471","article-title":"Data augmentation based on frequency warping for recognition of cleft palate speech","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Fujiwara"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10335"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2951856"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053725"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10674"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10896"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683803"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref22","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref23","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","author":"Jiang","year":"2019","journal-title":"arXiv:1910.09932"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref27","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0186"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.838537"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.014"},{"key":"ref34","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref35","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref36","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. ICLR","author":"Lan"},{"key":"ref37","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref38","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NeurIPS","author":"Caron"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/PIC50277.2020.9350839"},{"key":"ref46","first-page":"1","article-title":"In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning","volume-title":"Proc. ICLR","author":"Rizve"},{"key":"ref47","first-page":"1","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref49","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"Proc. ISCA IEEE Workshop Spontaneous Speech Process. Recognit.","author":"Maekawa"},{"key":"ref50","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1755"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12204278"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref54","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10463016.pdf?arnumber=10463016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T21:28:43Z","timestamp":1711488523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10463016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3374874","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}