{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T19:53:50Z","timestamp":1774727630465,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"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":[[2023,2,22]]},"DOI":"10.1109\/icai58407.2023.10136626","type":"proceedings-article","created":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T17:28:21Z","timestamp":1685640501000},"page":"209-213","source":"Crossref","is-referenced-by-count":11,"title":["Speaker Recognition in Realistic Scenario Using Multimodal Data"],"prefix":"10.1109","author":[{"given":"Saqlain Hussain","family":"Shah","sequence":"first","affiliation":[{"name":"University of Engineering and Technology Taxila"}]},{"given":"Muhammad Saad","family":"Saeed","sequence":"additional","affiliation":[{"name":"Swarm Robotics Lab NCRA"}]},{"given":"Shah","family":"Nawaz","sequence":"additional","affiliation":[{"name":"Deutsches Elektronen-Synchrotron DESY"}]},{"given":"Muhammad Haroon","family":"Yousaf","sequence":"additional","affiliation":[{"name":"University of Engineering and Technology Taxila"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Self-supervised learning of a facial attribute embedding from video","author":"wiles","year":"2018","journal-title":"British Machine Vision Conference"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.1918467"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref1","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-276"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/79.536825"},{"key":"ref19","first-page":"2","article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","volume":"14","author":"kenny","year":"2005","journal-title":"CRIM Montreal (Report) CRIM-06\/08-13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-274"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref25","article-title":"Soundnet: Learning sound representations from unlabeled video","volume":"29","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747704"},{"key":"ref22","first-page":"276","article-title":"On learning associations of faces and voices","author":"kim","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref21","article-title":"Learning branched fusion and orthogonal projection for face-voice association","author":"saeed","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1015"},{"key":"ref27","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Disjoint mapping network for cross-modal matching of voices and faces","author":"wen","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00184"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","location":"Islamabad, Pakistan","start":{"date-parts":[[2023,2,22]]},"end":{"date-parts":[[2023,2,23]]}},"container-title":["2023 3rd International Conference on Artificial Intelligence (ICAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10136637\/10136621\/10136626.pdf?arnumber=10136626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T17:48:53Z","timestamp":1687196933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10136626\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icai58407.2023.10136626","relation":{},"subject":[],"published":{"date-parts":[[2023,2,22]]}}}