{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:51:41Z","timestamp":1780775501294,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation"},{"name":"Korea Government"},{"name":"Development of Ultra-high Speech Quality Technology for Remote Multi-speaker Conference System","award":["2021-0-00456"],"award-info":[{"award-number":["2021-0-00456"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3463491","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T18:01:14Z","timestamp":1726682474000},"page":"4580-4595","source":"Crossref","is-referenced-by-count":6,"title":["Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7741-5365","authenticated-orcid":false,"given":"Jeong-Hwan","family":"Choi","sequence":"first","affiliation":[{"name":"School of Electronics, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0096-4371","authenticated-orcid":false,"given":"Joon-Young","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronics, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2610-2323","authenticated-orcid":false,"given":"Joon-Hyuk","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Electronics, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745552"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref6","article-title":"Deep Speaker: An end-to-end neural speaker embedding system","author":"Li","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3134566"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746639"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-402"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3244502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Deep Learn., Representations Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-88"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-383"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683443"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2106"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746247"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413564"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10932"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3182856"},{"key":"ref40","first-page":"1943","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph","year":"2017"},{"key":"ref41","first-page":"21","article-title":"Domain generalization on efficient acoustic scene classification using residual normalization","volume-title":"Proc. Workshop Detection, Classif. Acoust. Scenes, Events","author":"Kim","year":"2021"},{"key":"ref42","article-title":"HYU submission for the dcase 2022: fine-tuning method using device-aware data-random-drop for device-imbalanced acoustic scene classification","author":"Lee","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956079"},{"key":"ref44","article-title":"Multi-scale architecture and device-aware data-random-drop based fine-tuning method for acoustic scene classification","volume-title":"Proc. Workshop Detection, Classif. Acoust. Scenes, Events","author":"Lee","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/itaic58329.2023.10409026"},{"key":"ref46","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref49","first-page":"5776","article-title":"MINILM: Deep self-attention distillation for task-agnostic compression of pre-trained Transformers","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3007506"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref52","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Romero","year":"2015"},{"key":"ref53","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2020"},{"key":"ref54","first-page":"448","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref55","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413522"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref61","first-page":"818","article-title":"The speakers in the wild (SITW) speaker recognition database","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Castan","year":"2016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892002"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref64","first-page":"5814","article-title":"The IDlab Voxsrc-20 submission: Large margin fine-tuning and quality-aware score calibration in DNN based speaker verification","volume-title":"Proc. IEEE Int Conf. Acoust. Speech Signal Process.","author":"Thienpondt","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1751"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3091805"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref68","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref70","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2215"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947357"},{"key":"ref73","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":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2210"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402072"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10683974.pdf?arnumber=10683974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:51:16Z","timestamp":1732665076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10683974\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3463491","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}