{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T04:11:31Z","timestamp":1776744691254,"version":"3.51.2"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council GRF","award":["14200218"],"award-info":[{"award-number":["14200218"]}]},{"name":"Hong Kong Research Grants Council GRF","award":["14200220"],"award-info":[{"award-number":["14200220"]}]},{"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\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["PiH\/350\/20"],"award-info":[{"award-number":["PiH\/350\/20"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["InP\/275\/20"],"award-info":[{"award-number":["InP\/275\/20"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006355","name":"Shun Hing Institute of Advanced Engineering","doi-asserted-by":"publisher","award":["MMT-p1-19"],"award-info":[{"award-number":["MMT-p1-19"]}],"id":[{"id":"10.13039\/501100006355","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":[[2021]]},"DOI":"10.1109\/taslp.2021.3091805","type":"journal-article","created":{"date-parts":[[2021,6,23]],"date-time":"2021-06-23T19:48:40Z","timestamp":1624477720000},"page":"2267-2281","source":"Crossref","is-referenced-by-count":79,"title":["Recent Progress in the CUHK Dysarthric Speech Recognition System"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6202-5615","authenticated-orcid":false,"given":"Shansong","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengzhe","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3345-6923","authenticated-orcid":false,"given":"Shoukang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7886-439X","authenticated-orcid":false,"given":"Xurong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyu","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-1436","authenticated-orcid":false,"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6725-1160","authenticated-orcid":false,"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"1","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognition"},{"key":"ref72","year":"2020","journal-title":"Sox audio manipulation tool"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref70","article-title":"The HTK book","volume":"3","author":"young","year":"2006","journal-title":"Cambridge Univ Eng Dept"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref77","first-page":"2527","article-title":"An investigation into vocal tract length normalisation","author":"uebel","year":"0","journal-title":"Proc 6th Eur Conf Speech Commun Technol"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2609"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2275"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054130"},{"key":"ref78","doi-asserted-by":"crossref","first-page":"2171","DOI":"10.21437\/Eurospeech.1995-411","article-title":"Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system","author":"neto","year":"1995","journal-title":"Eurospeech"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472689"},{"key":"ref33","article-title":"Darts: Differentiable architecture search","author":"liu","year":"0","journal-title":"Proc ICLR"},{"key":"ref32","first-page":"1997","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3053"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref37","first-page":"6758","article-title":"Neural architecture search for LF-MMI trained time delay neural networks","author":"hu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref36","first-page":"12084","article-title":"DSNAS: Direct neural architecture search without parameter retraining","author":"hu","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref35","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"0","journal-title":"Proc ICLR"},{"key":"ref34","article-title":"Snas: Stochastic neural architecture search","author":"xie","year":"0","journal-title":"Proc ICLR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref62","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref61","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume":"117","author":"jaitly","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178831"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424244"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266376"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054596"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462290"},{"key":"ref69","first-page":"346","article-title":"Data augmentation using virtual microphone array synthesis and multi-resolution feature extraction for isolated word dysarthric speech recognition","volume":"14","author":"celin","year":"2020","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/1460-6984.12357"},{"key":"ref1","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 Phonet"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref24","first-page":"1","article-title":"Improved end-to-end dysarthric speech recognition via meta-learning based model re-initialization","author":"wang","year":"0","journal-title":"Proc Int Symp Chinese Spoken Language Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053549"},{"key":"ref26","first-page":"2751","article-title":"Purely sequence-trained neural networks for ASR based on lattice-free MMI","author":"povey","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref25","first-page":"3214","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.002"},{"key":"ref51","first-page":"51","article-title":"Audio-visual speech recognition for people with speech disorders","volume":"96","author":"salama","year":"2014","journal-title":"Int J Comput Appl"},{"key":"ref59","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"0","journal-title":"Proc ICLR"},{"key":"ref58","first-page":"4095","article-title":"Efficient neural architecture search via parameter sharing","author":"pham","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref57","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"0","journal-title":"Proc ICLR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref55","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref54","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","first-page":"1159","article-title":"Learning speaker-specific pronunciations of disordered speech","author":"christensen","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1541"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1536"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"ref12","first-page":"3669","article-title":"The CUHK dysarthric speech recognition systems for english and cantonese","author":"hu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682667"},{"key":"ref16","first-page":"329","article-title":"Development of a cantonese dysarthric speech corpus","author":"wong","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3084072"},{"key":"ref17","first-page":"792","article-title":"A dutch dysarthric speech database for individualized speech therapy research","author":"yilmaz","year":"0","journal-title":"LREC"},{"key":"ref84","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2950602"},{"key":"ref19","first-page":"1741","article-title":"Dysarthric speech database for universal access research","author":"kim","year":"0","journal-title":"Proc 9th Annu Conf Int Speech Commun Assoc"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref4","first-page":"357","article-title":"Stroke registry in malmö","volume":"23","author":"jerntorp","year":"1992"},{"key":"ref3","first-page":"140","article-title":"Speech therapy for Parkinson's disease","volume":"46","author":"scott","year":"1983","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/07434610012331279044"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-9924(00)00023-X"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"ref8","first-page":"3642","article-title":"Combining in-domain and out-of-domain speech data for automatic recognition of disordered speech","author":"christensen","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/10400435.2010.483646"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1751"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-5112"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2282"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683803"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078883"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2346"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09463679.pdf?arnumber=9463679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T09:05:38Z","timestamp":1672563938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9463679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3091805","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}