{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:08Z","timestamp":1784041088146,"version":"3.55.0"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"IITP","award":["2020-0-00004"],"award-info":[{"award-number":["2020-0-00004"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2022R1A2C2005529"],"award-info":[{"award-number":["NRF-2022R1A2C2005529"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BK21 FOUR","award":["4120200113769"],"award-info":[{"award-number":["4120200113769"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3352388","type":"journal-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T20:09:08Z","timestamp":1704917348000},"page":"6462-6474","source":"Crossref","is-referenced-by-count":18,"title":["AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8135-6625","authenticated-orcid":false,"given":"Jeong Hun","family":"Yeo","sequence":"first","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-0018","authenticated-orcid":false,"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6817-604X","authenticated-orcid":false,"given":"Jeongsoo","family":"Choi","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-3010","authenticated-orcid":false,"given":"Dae Hoe","family":"Kim","sequence":"additional","affiliation":[{"name":"Visual Intelligence Research Section, Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909819"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3210761"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3102433"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref17","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican1292-108"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref23","article-title":"Lip-listening: Mixing senses to understand lips using cross modality knowledge distillation for word-based models","author":"Mabrouk","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095029"},{"key":"ref25","article-title":"Spatio-temporal attention mechanism and knowledge distillation for lip reading","author":"Elashmawy","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00921"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6817"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3115626"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094693"},{"key":"ref32","article-title":"Memory networks,","author":"Weston","year":"2014"},{"key":"ref33","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.922789"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/6046.923820"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/6046.985551"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.236"},{"key":"ref40","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"ref42","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Van Den Oord","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref44","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref48","article-title":"Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading","author":"Weng","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref53","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_33"},{"key":"ref55","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11311"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747729"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref62","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413518"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref68","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3184480"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref72","article-title":"A fine-tuned wav2vec 2.0\/huBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref78","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref79","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref80","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1669"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10920"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01803"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191643"},{"key":"ref89","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Haliassos","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref91","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10387745.pdf?arnumber=10387745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:06:14Z","timestamp":1712862374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10387745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3352388","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}