{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:17:48Z","timestamp":1770830268311,"version":"3.50.1"},"reference-count":28,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018556","name":"Science and Technology Program of Suzhou","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018556","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100003536","name":"Youth Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100003536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446074","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11556-11560","source":"Crossref","is-referenced-by-count":4,"title":["Robust Wake Word Spotting With Frame-Level Cross-Modal Attention Based Audio-Visual Conformer"],"prefix":"10.1109","author":[{"given":"Haoxu","family":"Wang","sequence":"first","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China"}]},{"given":"Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China"}]},{"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Zhejiang Laboratory,Research Center for Intelligent Robotics, Research Institute of Interdisciplinary Innovation,Hangzhou,China"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414777"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1412"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-56"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747084"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414260"},{"key":"ref12","article-title":"Seeing Wake Words: Audio-Visual Keyword Spotting","volume-title":"Proc. BMVC","author":"Momeni"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747216"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096858"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095459"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11311"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746749"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10446074.pdf?arnumber=10446074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:53:44Z","timestamp":1722574424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446074","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}