{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:55Z","timestamp":1774420075748,"version":"3.50.1"},"reference-count":26,"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\/icassp49660.2025.10889645","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":0,"title":["LipReading for Low-resource Languages by Language Dynamic LoRA"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Zou","sequence":"first","affiliation":[{"name":"Xidian University,Guangzhou Institute of Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Liang","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Xidian University,Guangzhou Institute of Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Hearing by eye: The psychology of lip-reading","author":"Dodd","year":"1987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref4","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref8","article-title":"Learning audio-visual speech representation by masked multi-modal cluster prediction","author":"Shi","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462280"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902572"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00094-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855086"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.172"},{"key":"ref17","volume-title":"A course in phonetics","volume":"3","author":"Ladefoged","year":"2006"},{"key":"ref18","author":"Scao","year":"2023","journal-title":"Bloom: A 176b-parameter open-access multilingual language model"},{"key":"ref19","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.574"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"}],"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\/10889645.pdf?arnumber=10889645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:16Z","timestamp":1774416376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889645","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}