{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:40Z","timestamp":1775230060873,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688191","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"796-802","source":"Crossref","is-referenced-by-count":29,"title":["Audio-Visual Speech Recognition is Worth $32\\times 32\\times 8$ Voxels"],"prefix":"10.1109","author":[{"given":"Dmitriy","family":"Serdyuk","sequence":"first","affiliation":[{"name":"Google,New York,USA,10011"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Otavio","family":"Braga","sequence":"additional","affiliation":[{"name":"Google,New York,USA,10011"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Siohan","sequence":"additional","affiliation":[{"name":"Google,New York,USA,10011"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053974"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref31","article-title":"Data augmentation for deep neural network acoustic modeling","author":"cui","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref35","year":"0","journal-title":"Our principles - google AI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414160"},{"key":"ref10","author":"radford","year":"2019","journal-title":"Language Models are Unsupervised Multitask Learners"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref12","article-title":"ViViT: A video vision transformer","author":"arnab","year":"2021","journal-title":"ArXiv"},{"key":"ref13","article-title":"Is Space-Time attention all you need for video under-standing?","author":"bertasius","year":"2021","journal-title":"ArXiv"},{"key":"ref14","article-title":"LIPNET: Sentence-Level lipreading","author":"assael","year":"2016","journal-title":"ArXiv"},{"key":"ref15","article-title":"Lip reading sentences in the wild","author":"chung","year":"2016","journal-title":"CVPR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ICLRE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref3","author":"neti","year":"2000","journal-title":"Audio-visual speech recognition"},{"key":"ref6","article-title":"Very deep convolutional networks for Large-Scale image recognition","author":"simonyan","year":"0","journal-title":"ICLRE"},{"key":"ref29","author":"afouras","year":"2018","journal-title":"LRS3- TED A large-scale dataset for visual speech recognition"},{"key":"ref5","article-title":"ASR is all you need: cross-modal distillation for lip reading","author":"afouras","year":"2019","journal-title":"ICASSP"},{"key":"ref8","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref2","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ICLRE"},{"key":"ref9","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref20","article-title":"An image is worth 16×16 words, what is a video worth?","author":"sharir","year":"2021","journal-title":"ArXiv"},{"key":"ref22","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"tran","year":"2017","journal-title":"CVPR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref24","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML Representation Learning Worksop"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref25","article-title":"Rethinking spatiotemporal feature learning: Speed-Accuracy trade-offs in video classification","author":"xie","year":"2017","journal-title":"ECCV"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688191.pdf?arnumber=9688191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:55Z","timestamp":1652733715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688191","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}