{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:08:41Z","timestamp":1767978521639,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832196","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"43-48","source":"Crossref","is-referenced-by-count":1,"title":["Robust Audiovisual Speech Recognition Models with Mixture-of-Experts"],"prefix":"10.1109","author":[{"given":"Yihan","family":"Wu","sequence":"first","affiliation":[{"name":"Renmin University of China"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yichen","family":"Lu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[{"name":"Renmin University of China"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Recent advances in end-to-end automatic speech recognition","author":"Li","year":"2021","journal-title":"arXiv:2111.01690"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume":"202","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1194"},{"key":"ref6","article-title":"How2: A large-scale dataset for multimodal language understanding","volume":"abs\/1811.00347","author":"Sanabria","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-776"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383466"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref18","article-title":"Learning factored representations in a deep mixture of experts","author":"Eigen","year":"2014","journal-title":"ICLR"},{"key":"ref19","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"ICLR 2017"},{"key":"ref20","article-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv:2401.15947"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27872"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","first-page":"4835","article-title":"Joint ctc-attention based end-toend speech recognition using multi-task learning","author":"Kim","year":"2017","journal-title":"ICASSP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022656"},{"key":"ref26","article-title":"Branchformer: Parallel MLPattention architectures to capture local and global context for speech recognition and understanding","author":"Peng","year":"2022","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682750"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.216"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832196.pdf?arnumber=10832196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:09:25Z","timestamp":1737101365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832196","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}