{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:39:49Z","timestamp":1763105989538,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448048","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8195-8199","source":"Crossref","is-referenced-by-count":6,"title":["Audio-Visual Speech Recognition In-The-Wild: Multi-Angle Vehicle Cabin Corpus and Attention-Based Method"],"prefix":"10.1109","author":[{"given":"Alexandr","family":"Axyonov","sequence":"first","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"}]},{"given":"Dmitry","family":"Ryumin","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"}]},{"given":"Denis","family":"Ivanko","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"}]},{"given":"Alexey","family":"Kashevnik","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}]},{"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-914"},{"key":"ref3","first-page":"1555","article-title":"RUSAVIC Corpus: Russian Audio-Visual Speech in Cars","volume-title":"Proc. of the LREC","author":"Ivanko"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/math11122665"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-823"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43958-7_40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366579"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.5042758"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-424"},{"key":"ref14","first-page":"6786","article-title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","volume-title":"Proc. of the LREC","author":"Dai"},{"key":"ref15","first-page":"1141","article-title":"DAVIS: Driver\u2019s Audio-Visual Speech Recognition","volume-title":"Proc. of the INTERSPEECH","author":"Ivanko"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"article-title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","volume-title":"Proc. of the ICLR","author":"Shi","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3062752"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909819"},{"key":"ref23","article-title":"MediaPipe: A Framework for Perceiving and Processing Reality","volume-title":"Third workshop on computer vision for AR\/VR at CVPR","volume":"2019","author":"Lugaresi"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref25","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01308"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448048.pdf?arnumber=10448048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:40:34Z","timestamp":1722580834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448048","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}