{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:15:11Z","timestamp":1784304911263,"version":"3.55.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100020895","name":"MIT-IBM Watson AI Lab","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020895","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NDSEG Fellowship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3569210","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:46:35Z","timestamp":1747071995000},"page":"2144-2148","source":"Crossref","is-referenced-by-count":3,"title":["mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0063-3612","authenticated-orcid":false,"given":"Andrew","family":"Rouditchenko","sequence":"first","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7573-0620","authenticated-orcid":false,"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[{"name":"University of Tuebingen, Tuebingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6399-0679","authenticated-orcid":false,"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3097-360X","authenticated-orcid":false,"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1061"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref6","article-title":"Large language models are efficient learners of noise-robust speech recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10920"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889251"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref18","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681221"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref21","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref22","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref25","first-page":"21157","article-title":"u-HuBERT: Unified mixed-modal speech pretraining and zero-shot transfer to unlabeled modality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hsu","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"ref27","article-title":"AV-CPL: Continuous pseudo-labeling for audio-visual speech recognition","author":"Rouditchenko","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan","year":"2020"},{"key":"ref30","article-title":"Lrs3-ted: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref32","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Haliassos","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448473"},{"key":"ref34","article-title":"Unified speech recognition: A single model for auditory, visual, and audiovisual inputs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Haliassos","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094585"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446720"},{"key":"ref39","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref41","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref42","article-title":"PyTorch\n Lightning","year":"2023"},{"key":"ref43","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref44","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.697"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445891"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389795"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101811"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-503"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10999072.pdf?arnumber=10999072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:37:38Z","timestamp":1748540258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10999072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3569210","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}