{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:34:05Z","timestamp":1779338045191,"version":"3.51.4"},"reference-count":24,"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.2019.8683120","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"5791-5795","source":"Crossref","is-referenced-by-count":222,"title":["Utterance-level Aggregation for Speaker Recognition in the Wild"],"prefix":"10.1109","author":[{"given":"Weidi","family":"Xie","sequence":"first","affiliation":[{"name":"Visual Geometry Group, University of Oxford, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arsha","family":"Nagrani","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854622"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref12","article-title":"Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model","author":"shon","year":"2018","journal-title":"arXiv preprint arXiv 1809 04437"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref16","article-title":"NetVLAD: CNN architecture for weakly supervised place recognition","author":"arandjelovi?","year":"2016","journal-title":"Proc CVPR"},{"key":"ref17","article-title":"GhostVLAD for set-based face recognition","author":"zhong","year":"2018","journal-title":"Asian Conference on Computer Vision ACCV"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-92"},{"key":"ref19","article-title":"Unified hypersphere embedding for speaker recognition","author":"hajibabaei","year":"2018","journal-title":"arXiv preprint arXiv 1807 08312"},{"key":"ref4","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv preprint arXiv 1603 04467"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref5","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref7","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1705 02304"},{"key":"ref2","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":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738816"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1575"},{"key":"ref22","article-title":"Attention-based models for text-dependent speaker verification","author":"chowdhury","year":"2017","journal-title":"arXiv preprint arXiv 1710 10470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190128"}],"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\/08683120.pdf?arnumber=8683120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T18:22:21Z","timestamp":1753986141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683120","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}