{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:07:36Z","timestamp":1778717256287,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"publisher","award":["NRF2022R1A2C2005529,2022-000124"],"award-info":[{"award-number":["NRF2022R1A2C2005529,2022-000124"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00630","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6693-6703","source":"Crossref","is-referenced-by-count":1,"title":["Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations"],"prefix":"10.1109","author":[{"given":"Jeong Hun","family":"Yeo","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chae Won","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01312"},{"key":"ref6","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889251"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref13","article-title":"Unified speech recognition: A single model for auditory, visual, and audiovisual inputs","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Haliassos","year":"2024"},{"key":"ref14","article-title":"Visper: Multilingual audio-visual speech recognition","author":"Narayan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"International conference on machine learning","author":"Amodei","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref19","article-title":"Jointly learning visual and auditory speech representations from raw data","author":"Haliassos","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446720"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094585"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.697"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445891"},{"key":"ref30","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Mistral 7b","author":"Albert","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref35","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-4003"},{"key":"ref38","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"issue":"97","key":"ref39","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1800"},{"key":"ref41","article-title":"Completely unsupervised speech recognition by a generative adversarial network harmonized with iteratively refined hidden markov models","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Unsupervised speech recognition","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems, 34"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10712"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.166"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888774"},{"issue":"8","key":"ref47","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00430"},{"key":"ref49","article-title":"Sparks of large audio models: A survey and outlook","author":"Latif","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.860"},{"key":"ref51","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00094-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855086"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3444470"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref61","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref62","article-title":"Large language models are efficient learners of noise-robust speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hu","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1538"},{"key":"ref64","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.4324\/9780203430163"},{"key":"ref66","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445359.pdf?arnumber=11445359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:43Z","timestamp":1777530103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00630","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}