{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:18:03Z","timestamp":1776889083034,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888412","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["End-to-end acoustic-articulatory dysarthric speech recognition leveraging large-scale pretrained acoustic features"],"prefix":"10.1109","author":[{"given":"Zhengjun","family":"Yue","sequence":"first","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Multimedia Computing Group,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"196","article-title":"Clinical speech syndromes of the motor systems","volume-title":"Neurology for the Speech-Language Pathologist","author":"Gowers","year":"2001"},{"key":"ref2","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1159\/000511042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-484"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5120\/16770-6337"},{"key":"ref6","first-page":"70","article-title":"Learning mixed acoustic\/articulatory models for disabled speech","volume-title":"NIPS","author":"Rudzicz"},{"key":"ref7","article-title":"Deep learning of articulatory-based representations and applications for improving dysarthric speech recognition","volume-title":"Speech Communication; 13th ITG-Symposium","author":"Xiong"},{"key":"ref8","first-page":"226","article-title":"Relative invariance of articulatory movements, in invariance and variability in speech processes","author":"Fujimura","year":"1986","journal-title":"Lawrence Erlbaum"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-772"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2746"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3091805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-67"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746855"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119797"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2021.3076778"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414644"},{"key":"ref18","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in neural information processing systems","volume":"33","author":"Baevski"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10674"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-08-051584-7.50037-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053549"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389756"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2072499"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746989"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413625"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627093"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205766"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref35","article-title":"SoX - Sound eXchange","author":"Chris"},{"key":"ref36","article-title":"Snapshot ensembles: Train 1, get m for free","volume-title":"International Conference on Learning Representations","author":"Huang"},{"key":"ref37","article-title":"Librispeech language models, vocabulary and g2p models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054343"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref40","article-title":"WER statistical significance test"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888412.pdf?arnumber=10888412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:07Z","timestamp":1774416127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888412","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}