{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:45:03Z","timestamp":1784216703761,"version":"3.55.0"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Council GRF","award":["14200218"],"award-info":[{"award-number":["14200218"]}]},{"name":"Hong Kong Research Council GRF","award":["14200220"],"award-info":[{"award-number":["14200220"]}]},{"name":"Hong Kong Research Council GRF","award":["14200021"],"award-info":[{"award-number":["14200021"]}]},{"name":"Theme based Research Scheme","award":["T45-407\/19 N"],"award-info":[{"award-number":["T45-407\/19 N"]}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["ITS\/254\/19"],"award-info":[{"award-number":["ITS\/254\/19"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3195113","type":"journal-article","created":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T19:36:55Z","timestamp":1659123415000},"page":"2597-2611","source":"Crossref","is-referenced-by-count":43,"title":["Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7886-439X","authenticated-orcid":false,"given":"Mengzhe","family":"Geng","sequence":"first","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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\/0000-0003-2315-876X","authenticated-orcid":false,"given":"Zi","family":"Ye","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}],"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8475-4912","authenticated-orcid":false,"given":"Shujie","family":"Hu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}],"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2985066"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1755"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2174\/1567205014666171121114930"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2802914"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1159\/000487852"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2018.07.006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1536"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1228"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1904"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1318"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1161\/01.STR.23.3.357"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-150520"},{"key":"ref21","author":"lanier","year":"2010","journal-title":"J Speech Disorders"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/07434610012331279044"},{"key":"ref23","article-title":"Alzheimer's disease facts and figures","volume":"17","author":"wiley","year":"2021","journal-title":"Alzheimers Dement"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/525783"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404785"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/10400435.2010.483646"},{"key":"ref100","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414869"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-60"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178844"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1751"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.2000.0122"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3004.522"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413630"},{"key":"ref49","first-page":"3810","article-title":"Using the outputs of different automatic speech recognition paradigms for acoustic-and bert-based alzheimer's dementia detection through spontaneous speech","author":"pan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-484"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1720"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362068"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1384"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-697"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-173"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3091805"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053549"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053725"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-649"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref71","first-page":"2062","article-title":"On the Limit of English Conversational Speech Recognition","author":"t\u00fcske","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472689"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2511922"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472630"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270370"},{"key":"ref78","article-title":"Elderly acoustic models for large vocabulary continuous speech recognition","volume":"85","author":"baba","year":"2002","journal-title":"IEICE Trans Inf Syst"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947460"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541105"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-553"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1995-411"},{"key":"ref66","first-page":"1137","article-title":"A compact model for speaker-adaptive training","author":"anastasakos","year":"0","journal-title":"Proc Fourth Int Conf Spoken Lang Process ICSLP"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-214"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-303"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/5.237536"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2571"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044503"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2295"},{"key":"ref105","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-185"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746989"},{"key":"ref103","volume":"3","author":"young","year":"2002","journal-title":"The HTK Book"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref98","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume":"10","author":"berndt","year":"1994","journal-title":"ACM Trans Knowl Discov Data"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-313"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2222381"},{"key":"ref97","first-page":"1","article-title":"A sober look at the unsupervised learning of disentangled representations and their evaluation","volume":"21","author":"locatello","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-5112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1541"},{"key":"ref13","first-page":"3669","article-title":"The CUHK Dysarthric Speech Recognition Systems for English and Cantonese","author":"hu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2282"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413634"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-168"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2681691"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1080\/026992000298869","article-title":"Speech errors in cantonese speaking adults with cerebral palsy","volume":"14","author":"whitehill","year":"2000","journal-title":"Clin Linguist Phon"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1085"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/1460-6984.12357"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref19","first-page":"140","article-title":"Speech therapy for parkinson's disease","volume":"46","author":"scott","year":"1983","journal-title":"J Mach Learn Res"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-289"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-320"},{"key":"ref89","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.1994.00540180063015"},{"key":"ref87","first-page":"1299","article-title":"Speaker turn aware similarity scoring for diarization of speech-based cognitive assessments","author":"xu","year":"0","journal-title":"Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09844834.pdf?arnumber=9844834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:11:10Z","timestamp":1662408670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9844834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":108,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3195113","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}