{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:37Z","timestamp":1760245057083},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054440","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6794-6798","source":"Crossref","is-referenced-by-count":41,"title":["Frequency and Temporal Convolutional Attention for Text-Independent Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Sarthak","family":"Yadav","sequence":"first","affiliation":[]},{"given":"Atul","family":"Rai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2018-1158"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.21437\/Interspeech.2018-993"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2019-2616"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2019-1746"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2018.8461375"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP.2019.8683047"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/978-3-319-46493-0_38"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/Interspeech.2018-1015"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.21437\/Interspeech.2018-1929"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2019-2240"},{"key":"ref5","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":"ref8","first-page":"35","article-title":"Ghostvlad for set-based face recognition","author":"zhong","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref1","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.21437\/Interspeech.2017-1575","article-title":"Deep speaker embeddings for short-duration speaker verification","author":"bhattacharya","year":"2017","journal-title":"Proc Interspeech 2017"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref22","article-title":"Unified hypersphere embedding for speaker recognition","author":"hajibabaei","year":"2018","journal-title":"arXiv preprint arXiv 1807 08312"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Odyssey.2018-11"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054440.pdf?arnumber=9054440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:26:10Z","timestamp":1656375970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054440","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}