{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:14:58Z","timestamp":1784996098838,"version":"3.55.0"},"reference-count":130,"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\/4.0\/legalcode"}],"funder":[{"name":"Hong Kong RGC GRF","award":["14200220"],"award-info":[{"award-number":["14200220"]}]},{"name":"Hong Kong RGC GRF","award":["14200021"],"award-info":[{"award-number":["14200021"]}]},{"name":"Hong Kong RGC GRF","award":["TRS T45-407\/19 N"],"award-info":[{"award-number":["TRS T45-407\/19 N"]}]},{"name":"Innovation & Technology Fund","award":["ITS\/218\/21"],"award-info":[{"award-number":["ITS\/218\/21"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106255"],"award-info":[{"award-number":["62106255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project of Institute of Software, Chinese Academy of Sciences","award":["ISCAS-ZD-202401"],"award-info":[{"award-number":["ISCAS-ZD-202401"]}]},{"name":"Research Project of Institute of Software, Chinese Academy of Sciences","award":["ISCAS-JCMS-202306"],"award-info":[{"award-number":["ISCAS-JCMS-202306"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2023119"],"award-info":[{"award-number":["2023119"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"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.2024.3422839","type":"journal-article","created":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T17:37:07Z","timestamp":1720028227000},"page":"3561-3575","source":"Crossref","is-referenced-by-count":34,"title":["Self-Supervised ASR Models and Features for Dysarthric and Elderly Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8475-4912","authenticated-orcid":false,"given":"Shujie","family":"Hu","sequence":"first","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6714-6296","authenticated-orcid":false,"given":"Xurong","family":"Xie","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7886-439X","authenticated-orcid":false,"given":"Mengzhe","family":"Geng","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2637-7880","authenticated-orcid":false,"given":"Zengrui","family":"Jin","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8874-4167","authenticated-orcid":false,"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2206-0237","authenticated-orcid":false,"given":"Guinan","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Cui","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5823-3039","authenticated-orcid":false,"given":"Tianzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-3532","authenticated-orcid":false,"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6725-1160","authenticated-orcid":false,"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-5112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1541"},{"key":"ref7","first-page":"3669","article-title":"The CUHK dysarthric speech recognition systems for english and cantonese","volume-title":"Proc. INTERSPEECH","author":"Hu","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413634"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3323888"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3195113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-322"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2802914"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-150520"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2019.01.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1633"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2018.8612831"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414147"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1318"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2250"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746989"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1755"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3091805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-173"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053549"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1720"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-697"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362068"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1384"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-163"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-190"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10043"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10335"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10674"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097195"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205766"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095547"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746585"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/525783"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1904"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1228"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-297"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-712"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1159\/000487852"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2174\/1567205014666171121114930"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1519"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747167"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747856"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095593"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-943"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10942"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096770"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.1994.00540180063015"},{"key":"ref61","first-page":"1299","article-title":"Speaker turn aware similarity scoring for diarization of speech-based cognitive assessments","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Ann. Summit Conf.","author":"Xu","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-168"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414869"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462290"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747550"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-208"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2203"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-289"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053725"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-301"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1536"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5120\/16770-6337"},{"key":"ref77","first-page":"77","article-title":"Audio-visual speech recognition for a person with severe hearing loss using deep canonical correlation analysis","volume-title":"Proc. 1st Int. Workshop Challenges Hear. Assistive Technol.","author":"Takashima","year":"2017"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413625"},{"key":"ref79","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.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref82","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":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746952"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-816"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746250"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10896"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2023.3262001"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00280-z"},{"key":"ref93","article-title":"Dutch dysarthric speech recognition: Applying self-supervised learning to overcome the data scarcity issue","author":"Matsushima","year":"2022"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2072499"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2757263"},{"key":"ref96","first-page":"1","article-title":"Deep learning of articulatory-based representations and applications for improving dysarthric speech recognition","volume-title":"Proc. IEEE 13th ITG- Symp.","author":"Xiong","year":"2018"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.05.002"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-410"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1736"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383619"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2011-316"},{"key":"ref102","first-page":"1","article-title":"A multi-channel\/multi-speaker articulatory database for continuous speech recognition research","volume":"5","author":"Wrench","year":"2000","journal-title":"Phonus."},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1263"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-723"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095993"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638967"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-696"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2571"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113558"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683564"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1044\/2018_JSLHR-S-17-0360"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1121\/1.403994"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2012-263"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706709"},{"key":"ref117","article-title":"The HTK book","author":"Young","year":"2002"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533587"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref123","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. Workshop Autom. Speech Recogn. Understanding","author":"Povey","year":"2011"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-303"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref127","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090321"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.642647"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.624694"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10584335.pdf?arnumber=10584335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T17:58:50Z","timestamp":1722362330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10584335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":130,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3422839","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}