{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T04:30:36Z","timestamp":1783830636921,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1305200"],"award-info":[{"award-number":["2018YFB1305200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["62171183"],"award-info":[{"award-number":["62171183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tnnls.2022.3163771","type":"journal-article","created":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T19:30:23Z","timestamp":1649791823000},"page":"10028-10038","source":"Crossref","is-referenced-by-count":102,"title":["Multimodal Sparse Transformer Network for Audio-Visual Speech Recognition"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3115-0672","authenticated-orcid":false,"given":"Qiya","family":"Song","sequence":"first","affiliation":[{"name":"College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7029-8784","authenticated-orcid":false,"given":"Bin","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0585-9848","authenticated-orcid":false,"given":"Shutao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2830119"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978764"},{"key":"ref4","first-page":"23","article-title":"Audio-visual automatic speech recognition: An overview","volume":"22","author":"Potamianos","year":"2004","journal-title":"Issues Vis. Audio-Vis. Speech Process."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945992"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.1992.0009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref13","article-title":"Transformers with convolutional context for ASR","author":"Mohamed","year":"2019","journal-title":"arXiv:1904.11660"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053535"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref21","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016","journal-title":"arXiv:1611.01599"},{"key":"ref22","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00818"},{"key":"ref24","article-title":"Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading","author":"Weng","year":"2019","journal-title":"arXiv:1905.02540"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref26","article-title":"Explicit sparse transformer: Concentrated attention through explicit selection","author":"Zhao","year":"2019","journal-title":"arXiv:1912.11637"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45747-X_22"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref38","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv:1809.00496"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref40","article-title":"Multi-grained spatio-temporal modeling for lip-reading","author":"Wang","year":"2019","journal-title":"arXiv:1908.11618"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2480"},{"key":"ref43","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.12.006"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10336252\/09755926.pdf?arnumber=9755926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:09:33Z","timestamp":1708110573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9755926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":45,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3163771","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}