{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:39:31Z","timestamp":1783183171981,"version":"3.54.6"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["62171427"],"award-info":[{"award-number":["62171427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3541788","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T13:47:42Z","timestamp":1739454462000},"page":"7308-7320","source":"Crossref","is-referenced-by-count":3,"title":["Lightweight Audio-Visual Wake Word Spotting With Diverse Acoustic Knowledge Distillation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4315-2874","authenticated-orcid":false,"given":"Ke-Wei","family":"Li","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Chen","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-6531","authenticated-orcid":false,"given":"Heng-Shun","family":"Zhou","sequence":"additional","affiliation":[{"name":"iFlytek Research, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0770-0507","authenticated-orcid":false,"given":"Sabato","family":"Marco Siniscalchi","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, University of Palermo, Palermo, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0315-1042","authenticated-orcid":false,"given":"Shu-Tong","family":"Niu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Fu","family":"Xiong","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414777"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86362-3_30"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054538"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2222"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3071461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10650"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747216"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682868"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-592"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3450021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3018487"},{"key":"ref18","first-page":"11863","article-title":"SimAM: A simple, parameter-free attention module for convolutional neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Yang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150338"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9030"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-968"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953242"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74695-9_23"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846306"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"ref29","first-page":"3251","article-title":"An end-to-end architecture for keyword spotting and voice activity detection","volume-title":"Proc. Interspeech","author":"Park"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02142-3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907840"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451096"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.10"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096858"},{"key":"ref40","first-page":"822","article-title":"Why do larger models generalize better? a theoretical perspective via the xor problem","volume-title":"Proc. ICML","author":"Brutzkus"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref42","first-page":"4739","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS","author":"Hinton"},{"key":"ref43","first-page":"2654","article-title":"Do deep nets really need to be deep","volume-title":"Proc. NIPS","author":"Ba"},{"key":"ref44","first-page":"1","article-title":"Do deep convolutional nets really need to be deep and convolutional?","volume-title":"Proc. ICLR","author":"Urban"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3421277"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3343112"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3237183"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085755"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00768"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802909"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060162"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00048"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.96"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3350695"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680777"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref63","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1210"},{"key":"ref68","article-title":"On stability and convergence of a three-layer semi-discrete scheme for an abstract analogue of the ball integro-differential equation","author":"Rogava","year":"2022","journal-title":"arXiv:2201.12345"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095459"},{"key":"ref70","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10884848.pdf?arnumber=10884848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:48:26Z","timestamp":1755546506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10884848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":70,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3541788","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}