{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:01:52Z","timestamp":1783440112912,"version":"3.54.6"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445949","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12341-12345","source":"Crossref","is-referenced-by-count":9,"title":["Exploiting Audio-Visual Features with Pretrained AV-HuBERT for Multi-Modal Dysarthric Speech Reconstruction"],"prefix":"10.1109","author":[{"given":"Xueyuan","family":"Chen","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuejiao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Disong","family":"Wang","sequence":"additional","affiliation":[{"name":"Vocal Engineering Technologies Limited,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29613-0_100981"},{"issue":"2","key":"ref2","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":"Clinical linguistics & phonetics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.1"},{"key":"ref5","first-page":"86","article-title":"Hilvoice: Human-in-the-loop style selection for elder-facing speech synthesis","volume-title":"ISCSLP","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2016.7732175"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2644258"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-664"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054596"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-285"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682566"},{"key":"ref12","first-page":"3669","article-title":"The cuhk dysarthric speech recognition systems for english and cantonese","volume-title":"INTERSPEECH","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref14","author":"Simonyan","year":"2014","journal-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1536"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref18","author":"Shi","year":"2022","journal-title":"Learning audio-visual speech representation by masked multimodal cluster prediction"},{"key":"ref19","author":"Ren","year":"2020","journal-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech"},{"key":"ref20","first-page":"7193","article-title":"Unsupervised multi-scale expressive speaking style modeling with hierarchical context information for audiobook speech synthesis","volume-title":"COLING","author":"Chen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446352"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref24","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref25","article-title":"Superseded-cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref27","author":"Zeiler","year":"2012","journal-title":"Adadelta: an adaptive learning rate method"},{"key":"ref28","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref30","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445949.pdf?arnumber=10445949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:43:39Z","timestamp":1722573819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445949","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}