{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:21:50Z","timestamp":1776529310036,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683477","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3995-3999","source":"Crossref","is-referenced-by-count":36,"title":["Noise-tolerant Audio-visual Online Person Verification Using an Attention-based Neural Network Fusion"],"prefix":"10.1109","author":[{"given":"Suwon","family":"Shon","sequence":"first","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462122"},{"key":"ref12","article-title":"Audio-visual Speech Recognition","author":"neti","year":"2000","journal-title":"Tech Rep IDIAP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28649-3_60"},{"key":"ref14","article-title":"Robust end-to-end deep audiovisual speech recognition","author":"sanabria","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref17","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","article-title":"Learning to localize sound source in visual scenes","author":"senocak","year":"2018","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_2"},{"key":"ref3","article-title":"Seeing voices and hearing faces: Cross-modal biometric matching","author":"nagrani","year":"2018","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref6","first-page":"176","article-title":"Mul-timodal Person Recognition using Unconstrained Audio and Video","author":"choudhury","year":"1999","journal-title":"Proc Int Conf Audio- and Video-Based Person Authentication"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref5","article-title":"On learning associations of faces and voices","author":"kim","year":"2018","journal-title":"Asian Conference on Computer Vision (ACCV)"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MMUL.2006.37","article-title":"Multimodal Person Recognition for Human-vehicle Interaction","volume":"13","author":"thomas","year":"2006","journal-title":"IEEE Multimedia"},{"key":"ref7","first-page":"258","article-title":"Audio, Video and Multimodal Person Identification in a Smart Room","author":"luque","year":"2006","journal-title":"Classification of Events Activities and Relationships Evaluation and Workshop"},{"key":"ref2","article-title":"Hearing faces and seeing voices”: Amodal coding of person identity in the human brain","volume":"6","author":"hasan","year":"2016","journal-title":"Scientific Reports"},{"key":"ref9","article-title":"Multi-modal user authentication from video for mobile or variable-environment applications","author":"hazen","year":"2007","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0040326"},{"key":"ref20","article-title":"Frame-level Speaker Embeddings for Text-independent Speaker Recognition and Analysis of End-to-end Model","author":"shon","year":"2018","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagraniy","year":"2017","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref24","year":"0","journal-title":"NIST 2016 speaker recognition evaluation plan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0040326"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248106"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683477.pdf?arnumber=8683477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:37:44Z","timestamp":1755909464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683477","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}