{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:21:18Z","timestamp":1777656078681,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639643","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"513-520","source":"Crossref","is-referenced-by-count":101,"title":["Audio-Visual Speech Recognition with a Hybrid CTC\/Attention Architecture"],"prefix":"10.1109","author":[{"given":"Stavros","family":"Petridis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Themos","family":"Stafylakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Tzimiropoulos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Speech commands: A public dataset for single-word speech recognition","author":"warden","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref30","article-title":"Attention-based audio-visual fusion for robust automatic speech recognition","author":"sterpu","year":"2018","journal-title":"arXiv preprint arXiv 1809 01728"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"ref12","article-title":"Lipnet: Sentence-level lipreading","author":"assael","year":"2016","journal-title":"arXiv preprint arXiv 1611 01599"},{"key":"ref13","article-title":"Large-scale visual speech recognition","author":"shillingford","year":"2018","journal-title":"arXiv preprint arXiv 1807 05162"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"3652","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with LSTMs for lipreading","volume":"9","author":"stafylakis","year":"2017","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/AVSP.2017-8","article-title":"End-to-end audiovisual fusion with LSTMs","author":"petridis","year":"2017","journal-title":"Proc Conf Auditory-Visual Speech Processing"},{"key":"ref17","first-page":"1","article-title":"OuluVS2: A multi-view audiovisual database for non-rigid mouth motion analysis","author":"anina","year":"2015","journal-title":"IEEE FG"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref19","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"ACCV"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref4","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc of ICML"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref3","first-page":"45","article-title":"Prediction-based audiovisual fusion for classification of non-linguistic vocalisations","volume":"7","author":"petridis","year":"2015","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref6","article-title":"Integration of deep bottleneck features for audio-visual speech recognition","author":"ninomiya","year":"2015","journal-title":"InterSpeech"},{"key":"ref29","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv preprint arXiv 1809 02108"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.389"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-721"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref22","article-title":"Lip reading in profile","author":"chung","year":"2017","journal-title":"British Machine Vision Conference"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00088"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref23","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"kannan","year":"2017","journal-title":"arXiv preprint arXiv 1712 01996"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639643.pdf?arnumber=8639643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T06:36:40Z","timestamp":1643265400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639643","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}