{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:30:50Z","timestamp":1788888650786,"version":"build-2803163510"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002790","name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","doi-asserted-by":"publisher","award":["CRDPJ 533919-18"],"award-info":[{"award-number":["CRDPJ 533919-18"]}],"id":[{"id":"10.13039\/501100002790","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892054","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Fine-grained Early Frequency Attention for Deep Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Amirhossein","family":"Hajavi","sequence":"first","affiliation":[{"name":"Labs Research Institute, Queen&#x0027;s University,Dept. ECE and Ingenuity,Kingston,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[{"name":"Labs Research Institute, Queen&#x0027;s University,Dept. ECE and Ingenuity,Kingston,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683649"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref12","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":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref14","article-title":"Attention-aware fusion rgb-d face recognition","author":"uppal","year":"2021","journal-title":"Transactions on Information Forensics and Security"},{"key":"ref15","article-title":"Capsule attention for multimodal eeg and eog spatiotemporal representation learning with application to driver vigilance estimation","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2956998"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1575"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461587"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref28","article-title":"Unified Hypersphere Embedding for Speaker Recognition","author":"hajibabaei","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053893"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2661705"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414722"},{"key":"ref2","first-page":"1","article-title":"Fluent-net: End-to-end detection of stuttered speech disfluencies with deep learning","author":"kourkounakis","year":"0","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683332"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref20","first-page":"4305","article-title":"Self Multi-Head Attention for Speaker Recognition","author":"safari","year":"2019","journal-title":"InterSpeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.046"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383579"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682676"},{"key":"ref26","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054440"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892054.pdf?arnumber=9892054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:58:46Z","timestamp":1667516326000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892054","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}