{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:48:42Z","timestamp":1756000122577,"version":"3.37.3"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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","award":["U1836219","62101523"],"award-info":[{"award-number":["U1836219","62101523"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hefei Municipal Natural Science Foundation","award":["2022012"],"award-info":[{"award-number":["2022012"]}]},{"name":"USTC Research Funds of the Double First-Class Initiative"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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":[[2023]]},"DOI":"10.1109\/taslp.2022.3231709","type":"journal-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T18:35:30Z","timestamp":1672857330000},"page":"643-655","source":"Crossref","is-referenced-by-count":7,"title":["Memory Storable Network Based Feature Aggregation for Speaker Representation Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1621-7311","authenticated-orcid":false,"given":"Bin","family":"Gu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3779-7944","authenticated-orcid":false,"given":"Wu","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1124-0854","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.06.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1515"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461587"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1422"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414704"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054448"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1704"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1845"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362054"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054440"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.248"},{"key":"ref27","first-page":"4905","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Luo","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2240"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-111"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref33","article-title":"Rep works in speaker verification","volume-title":"CoRR","volume":"abs\/2110.09720","author":"Ma","year":"2021"},{"article-title":"TMS: A temporal multi-scale backbone design for speaker embedding","year":"2022","author":"Zhang","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Learning speaker-specific characteristics with deep neural architecture","year":"2012","author":"Salman","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref38","article-title":"NIST SRE CTS superset: A large-scale dataset for telephony speaker recognition","volume-title":"CoRR","volume":"abs\/2108.07118","author":"Sadjadi","year":"2021"},{"key":"ref39","first-page":"2441","article-title":"The mixer 6 corpus: Resources for cross-channel and text independent speaker recognition","volume-title":"Proc. LREC","author":"Brandschain","year":"2010"},{"article-title":"Switchboard-2 phase","year":"1998","author":"Graff","key":"ref40"},{"article-title":"Switchboard-2 phase","year":"1999","author":"Graff","key":"ref41"},{"article-title":"Switchboard cellular part 1 audio","year":"2001","author":"Graff","key":"ref42"},{"article-title":"Switchboard-2 phase","year":"2002","author":"Graff","key":"ref43"},{"article-title":"Switchboard cellular part 2 audio","year":"2001","author":"Graff","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1351"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1521"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1137"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1837"},{"key":"ref52","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. Workshop Autom. Speech Recognit. Understanding, IEEE Conf. Signal Process. Soc.","author":"Povey","year":"2011"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683445"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682852"},{"key":"ref55","first-page":"1","article-title":"NARA-WPE: A python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing","volume-title":"Proc. Speech Commun.; 13th ITG-Symp. VDE","author":"Drude","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3091932"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153270"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101383"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747778"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3146"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016498"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref65","article-title":"Musan: A music, speech, and noise corpus","volume-title":"CoRR","volume":"abs\/1510.08484","author":"Snyder","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10006409.pdf?arnumber=10006409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T02:55:29Z","timestamp":1707447329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10006409\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3231709","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}