{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:17:51Z","timestamp":1782386271446,"version":"3.54.5"},"reference-count":47,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176106"],"award-info":[{"award-number":["62176106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Scientific Research Project of School of Emergency Management of Jiangsu University","award":["KY-A-01"],"award-info":[{"award-number":["KY-A-01"]}]},{"name":"Key Project of National Nature Science Foundation of China","award":["U1836220"],"award-info":[{"award-number":["U1836220"]}]},{"name":"Jiangsu key research and development plan industry foresight and key core technology","award":["BE2020036"],"award-info":[{"award-number":["BE2020036"]}]},{"name":"Post-graduate Research & Practice Innovation Program of Jiangsu Province","award":["KYCX22_3668"],"award-info":[{"award-number":["KYCX22_3668"]}]},{"name":"MTRAC Grant for Advanced Computing Technologies"}],"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.2024.3369529","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:58:58Z","timestamp":1709146738000},"page":"1687-1698","source":"Crossref","is-referenced-by-count":19,"title":["On Local Temporal Embedding for Semi-Supervised Sound Event Detection"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-0660","authenticated-orcid":false,"given":"Lijian","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0616-4431","authenticated-orcid":false,"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8133-7809","authenticated-orcid":false,"given":"Ming","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Wayne State University, Detroit, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548097"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747834"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053609"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3014737"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747762"},{"key":"ref10","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414931"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053073"},{"key":"ref13","first-page":"376","article-title":"Sound event detection by consistency training and pseudo-labeling with feature-pyramid convolutional recurrent neural networks","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Chen","year":"2021"},{"key":"ref14","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niizumi","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref16","first-page":"135","article-title":"DEPA: Self-supervised audio embedding for depression detection","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Dinkel","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2989575"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3088949"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref22","first-page":"100","article-title":"Conformer-based sound event detection with semi-supervised learning and data augmentation","volume-title":"Proc. Detection Classification Acoust. Scenes Events Workshop","author":"Miyazaki","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app12052626"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-684"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096367"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2016.08.002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053584"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA54004.2022.9786322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3178591"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980285"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref36","first-page":"1","article-title":"Masked autoencoders that listen","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Bernie","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00194"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109282"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3228167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref43","first-page":"205","article-title":"Improving sound event detection in domestic environments using sound separation","volume-title":"Proc. Detection Classification Acoust. Scenes Events Workshop","author":"Turpault","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414774"},{"key":"ref45","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Jort","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref47","first-page":"200","article-title":"Training sound event detection on a heterogeneous dataset","volume-title":"Proc. Detection Classification Acoust. Scenes Events Workshop","author":"Turpault","year":"2020"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10452873.pdf?arnumber=10452873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T18:23:36Z","timestamp":1725647016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10452873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3369529","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}