{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T15:30:08Z","timestamp":1749569408794,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/smc53992.2023.10394108","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:32:04Z","timestamp":1706553124000},"page":"572-577","source":"Crossref","is-referenced-by-count":1,"title":["An End-to-End Mandarin Audio-Visual Speech Recognition Model with a Feature Enhancement Module"],"prefix":"10.1109","author":[{"given":"Jinxin","family":"Wang","sequence":"first","affiliation":[{"name":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Technology Sydney,Sydney,Australia"}]},{"given":"Zhongwen","family":"Guo","sequence":"additional","affiliation":[{"name":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"}]},{"given":"Xiaomei","family":"Li","sequence":"additional","affiliation":[{"name":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"}]},{"given":"Weigang","family":"Wang","sequence":"additional","affiliation":[{"name":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICIP40778.2020.9190894"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASLP.2019.2950602"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TASLP.2021.3078883"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2018.8461326"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/6046.865479"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2017.7952625"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/interspeech.2022-10920"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICPR48806.2021.9412454"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPRW.2018.00131"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-030-58574-7_1"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/978-3-030-58452-8_45"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.23915\/distill.00003"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/MIPR.2018.00043"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1145\/3347320.3357690"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref17","first-page":"448","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","volume-title":"ICML","author":"Ioffe","year":"2015"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1016\/j.neunet.2020.09.017"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref20","first-page":"1","article-title":"Network in network","volume":"abs\/1312.4400","author":"Lin","year":"2013","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref23","article-title":"EdgeCNN: Convolutional neural network classification model with small inputs for edge computing","author":"Yang","year":"2019","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2018.00082"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref26","article-title":"High-resolution representations for labeling pixels and regions","author":"Sun","year":"2019","journal-title":"arXiv preprint"},{"volume-title":"Audio fingerprinting system: Mirex 2015 submissions","year":"2015","author":"Wang","key":"ref27"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/FG.2019.8756582"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1145\/3338533.3366579"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ICPR48806.2021.9412817"},{"key":"ref32","first-page":"76","article-title":"Learrning to lip read words by watching videos","volume-title":"CVIU","volume":"173","author":"Chuang","year":"2018"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref34","first-page":"1","article-title":"Learn an effective lip reading model without pains","volume":"abs\/2011.07557","author":"Feng","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"PMLR","author":"Amodei","year":"2016"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICASSP.2017.7953077"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/TASLP.2020.3036237"}],"event":{"name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2023,10,1]]},"location":"Honolulu, Oahu, HI, USA","end":{"date-parts":[[2023,10,4]]}},"container-title":["2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10391856\/10393862\/10394108.pdf?arnumber=10394108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T06:57:19Z","timestamp":1709449039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10394108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/smc53992.2023.10394108","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}