{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:40Z","timestamp":1775230060245,"version":"3.50.1"},"reference-count":32,"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"}],"funder":[{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890272","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["DCIM-AVSR: Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Wang","sequence":"first","affiliation":[{"name":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"}]},{"given":"Haotian","family":"Jiang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"}]},{"given":"Haolin","family":"Huang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"}]},{"given":"Yu","family":"Fang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"}]},{"given":"Mengjie","family":"Xu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak super-vision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10500"},{"key":"ref6","article-title":"WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System","volume-title":"Proc. the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)","author":"Xiao"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625974"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446720"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3115626"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/1729881420976082"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446532"},{"key":"ref14","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Shi"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447487"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446769"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2889052"},{"key":"ref22","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097011"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448050"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref31","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Haliassos"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"}],"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\/10890272.pdf?arnumber=10890272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:27Z","timestamp":1774416267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890272","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}