{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T10:40:26Z","timestamp":1778668826845,"version":"3.51.4"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"RGC of Hong Kong SAR","award":["PolyU 152137\/17E"],"award-info":[{"award-number":["PolyU 152137\/17E"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971371"],"award-info":[{"award-number":["61971371"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3153267","type":"journal-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T16:46:56Z","timestamp":1646066816000},"page":"944-957","source":"Crossref","is-referenced-by-count":10,"title":["Aggregating Frame-Level Information in the Spectral Domain With Self-Attention for Speaker Embedding"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9580-2414","authenticated-orcid":false,"given":"Youzhi","family":"Tu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8854-3760","authenticated-orcid":false,"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref2","article-title":"Deepspeaker: An end-to-end neural speaker embedding system","author":"Li","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","first-page":"4700","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Huang","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-30"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2979"},{"key":"ref12","first-page":"2448","article-title":"Analysis of BUT submission in far-field scenarios of VOiCES 2019 challenge","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Matjka","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054134"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3004760"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053217"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2264"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-9"},{"key":"ref21","first-page":"2449","article-title":"Spectral representations for convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rippel","year":"2015"},{"key":"ref22","volume-title":"Discrete-Time Speech Signal Processing: Principles and Practice","author":"Quatieri","year":"2002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414094"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162950"},{"key":"ref25","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682712"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2616"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054440"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref34","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref35","volume-title":"Discrete-Time Signal Processing.","author":"Oppenheim","year":"1999"},{"key":"ref36","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rahaman","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref38","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit","year":"2017"},{"key":"ref39","volume-title":"Digital Image Processing","author":"Gonzalez","year":"2006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1599"},{"key":"ref41","first-page":"17 283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1768-8_27"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-14832-4_12"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1837"},{"key":"ref46","article-title":"NIST 2016 speaker recognition evaluation plan","year":"2016"},{"key":"ref47","article-title":"NIST 2018 speaker recognition evaluation plan","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref49","first-page":"1567","article-title":"Analysis of score normalization in multilingual speaker recognition","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Matjka","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1978.10837"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09722993.pdf?arnumber=9722993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T18:57:30Z","timestamp":1705517850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9722993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3153267","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.15168573","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.15168573.v1","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}