{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:30:23Z","timestamp":1783791023043,"version":"3.55.0"},"reference-count":50,"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\/icassp49660.2025.10889251","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":21,"title":["Large Language Models are Strong Audio-Visual Speech Recognition Learners"],"prefix":"10.1109","author":[{"given":"Umberto","family":"Cappellazzo","sequence":"first","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglie","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Falavigna","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Brutti","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2889052"},{"key":"ref2","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"ICLR"},{"key":"ref3","article-title":"Jointly learning visual and auditory speech representations from raw data","author":"Haliassos","year":"2023","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10920"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446532"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"ref10","article-title":"u-HuBERT: Unified mixed-modal speech pretraining and zero-shot transfer to unlabeled modality","author":"Hsu","year":"2022","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448473"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446720"},{"key":"ref15","article-title":"Mistral\u2013a journey towards reproducible language model training","author":"Karamcheti","year":"2021"},{"key":"ref16","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref18","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024"},{"key":"ref19","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref21","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref25","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"ref28","article-title":"Macaw-llm: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3532688"},{"key":"ref30","article-title":"Crema: Multimodal compositional video reasoning via efficient modular adaptation and fusion","author":"Yu","year":"2024"},{"key":"ref31","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref32","article-title":"Large language models are efficient learners of noise-robust speech recognition","author":"Hu","year":"2024","journal-title":"ICLR"},{"key":"ref33","article-title":"An embarrassingly simple approach for llm with strong asr capacity","author":"Ma","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref37","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref39","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref41","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref44","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445891"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832305"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"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\/10889251.pdf?arnumber=10889251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:46Z","timestamp":1774416286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889251","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}