{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T08:28:24Z","timestamp":1788164904678,"version":"build-2803163510"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448047","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12787-12791","source":"Crossref","is-referenced-by-count":10,"title":["Self-Supervised Adaptive AV Fusion Module for Pre-Trained ASR Models"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Simic","sequence":"first","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1114"},{"key":"ref2","author":"Radford","year":"2022","journal-title":"Robust speech recognition via large-scale weak supervision"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Baevski"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094849"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193049"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095883"},{"key":"ref15","article-title":"Lip reading in profile","volume-title":"British Machine Vision Conference","author":"Chung"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2796118"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref19","first-page":"1","article-title":"Deep audio-visual speech recognition","volume":"PP","author":"Afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref20","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Haliassos"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref22","first-page":"1","article-title":"Autoavsr: Audio-visual speech recognition with automatic labels","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ma"},{"key":"ref23","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proceedings of the 10th Inter- national Conference on Learning Representations (ICLR)","author":"Shi"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref25","author":"Afouras","year":"2018","journal-title":"Lrs3-ted: a large-scale dataset for visual speech recognition"},{"key":"ref26","author":"Snyder","year":"2015","journal-title":"MUSAN: A Music, Speech, and Noise Corpus"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"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\/10448047.pdf?arnumber=10448047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:40:21Z","timestamp":1722580821000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448047","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}