{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:37:10Z","timestamp":1792514230107,"version":"4.5.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462122","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"3031-3035","source":"Crossref","is-referenced-by-count":21,"title":["Audio-Visual Person Recognition in Multimedia Data From the Iarpa Janus Program"],"prefix":"10.1109","author":[{"given":"Gregory","family":"Sell","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Duh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Snyder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dave","family":"Etter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Garcia-Romero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Workshop on Multi-view Lipreading ACCV"},{"key":"ref30","first-page":"1895","article-title":"The DET Curve in Assessment of Detection Task Performance","author":"martin","year":"1997","journal-title":"Proceedings of the European Conference on Speech Communication and Technology"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref12","article-title":"Large-Scale Speaker Identification","author":"schmidt","year":"2014","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","article-title":"Face Recognition in Unconstrained Videos with Matched Background Similarity","author":"wolf","year":"2011","journal-title":"proceedings of CVPR"},{"key":"ref14","article-title":"Labeled Faces in the Wild: A Database for Studying Face Recognition","author":"huang","year":"2007","journal-title":"Technical Report 07–49"},{"key":"ref15","article-title":"Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-based Classification","author":"ortiz","year":"2013","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.04.018"},{"key":"ref17","article-title":"On evaluating face tracks in movies","author":"ozerov","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Image Processing"},{"key":"ref18","author":"bansal","year":"2017","journal-title":"The do's and don'ts for cnn-based face verification"},{"key":"ref19","article-title":"IARPA Janus Benchmark-B Face Dataset","author":"whitelam","year":"2017","journal-title":"proceedings of CVPR"},{"key":"ref28","article-title":"FaceNet: a Unified Embedding for Face Recognition and Clustering","author":"schroff","year":"2015","journal-title":"proceedings of CVPR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-140460"},{"key":"ref27","article-title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","author":"zhang","year":"2015","journal-title":"IEEE Signal Processing Letters"},{"key":"ref3","article-title":"TRECVID 2016: Evaluation Video Search, Video Event Detection, Localization, and Hyperlinking","author":"awad","year":"2016","journal-title":"Proceedings of TRECVID 2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref29","article-title":"On calibration of language recognition scores","author":"br\u00fcmmer","year":"2006","journal-title":"Proc Odyssey"},{"key":"ref5","article-title":"Audio-Visual Deep Learning for Noise Robust Speech Recognition","author":"huang","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","article-title":"Mul-timodeal Person Discovery in Broadcast TV at MediaEval 2015","author":"poignant","year":"2015","journal-title":"MediaEval Workshop"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2009.4959999","article-title":"Audiovisual Celebrity Recognition in Unconstrained Web Videos","author":"sargin","year":"2009","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref2","author":"hoover","year":"2017","journal-title":"Putting a Face to the Voice Fusing Audio and Visual Signals Across a Video to Determine Speakers"},{"key":"ref9","article-title":"Mul-timodal Person Discovery in Broadcast TV at MediaEval 2016","author":"bredin","year":"2016","journal-title":"MediaEval Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.47"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref21","first-page":"531","article-title":"Probabilistic Linear Discriminant Analysis","author":"ioffe","year":"2006","journal-title":"ECCV"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1137"},{"key":"ref23","year":"2010","journal-title":"The NIST Year 2010 Speaker Recognition Evaluation Plan"},{"key":"ref26","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proceedings of Interspeech"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462122.pdf?arnumber=8462122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T10:55:13Z","timestamp":1662116113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462122","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}