{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:16:51Z","timestamp":1787012211927,"version":"build-2736575974"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747704","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"7057-7061","source":"Crossref","is-referenced-by-count":36,"title":["Fusion and Orthogonal Projection for Improved Face-Voice Association"],"prefix":"10.1109","author":[{"given":"Muhammad Saad","family":"Saeed","sequence":"first","affiliation":[{"name":"University of Engineering and Technology Taxila,Swarm Robotics Lab (SRL)-NCRA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Haris","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shah","family":"Nawaz","sequence":"additional","affiliation":[{"name":"Pattern Analysis & Computer Vision (PAVIS) - Istituto Italiano di Tecnologia (IIT)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Haroon","family":"Yousaf","sequence":"additional","affiliation":[{"name":"University of Engineering and Technology Taxila,Swarm Robotics Lab (SRL)-NCRA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Del Bue","sequence":"additional","affiliation":[{"name":"Pattern Analysis & Computer Vision (PAVIS) - Istituto Italiano di Tecnologia (IIT)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref11","article-title":"Gated multi-modal units for information fusion","author":"arevalo","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2229"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00657"},{"key":"ref15","article-title":"Git loss for deep face recognition","author":"calefati","year":"2018","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref5","first-page":"276","article-title":"On learning associations of faces and voices","author":"kim","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"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\/CVPR46437.2021.01608"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00184"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747704.pdf?arnumber=9747704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:11:15Z","timestamp":1661184675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747704","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}