{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:35:54Z","timestamp":1775626554650,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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\/501100002380","name":"Hanyang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002380","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434748","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion"],"prefix":"10.1109","author":[{"given":"DongHoon","family":"Lim","sequence":"first","affiliation":[{"name":"Hanyang University,Dept. Artificial Intelligence,Seoul,Republic of Korea"}]},{"given":"YoungChae","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanyang University,Dept. Artificial Intelligence,Seoul,Republic of Korea"}]},{"given":"Dong-Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea"}]},{"given":"Da-Hee","family":"Yang","sequence":"additional","affiliation":[{"name":"Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea"}]},{"given":"Joon-Hyuk","family":"Chang","sequence":"additional","affiliation":[{"name":"Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888423"},{"key":"ref2","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Shi"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref5","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889566"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688191"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref12","article-title":"MUSAN: A music, speech, and noise corpus","volume":"abs\/1510.08484","author":"Snyder","year":"2015","journal-title":"ArXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588783"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50563-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486455"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref25","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref26","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. International conference on machine learning","author":"Arjovsky"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","volume":"abs\/1412.6980","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"ref28","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv:1809.00496"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00150"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2081"},{"key":"ref33","article-title":"Decoupled weight decay regularization","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Loshchilov"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434748.pdf?arnumber=11434748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:12Z","timestamp":1775192352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434748","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}