{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T12:43:19Z","timestamp":1781354599434,"version":"3.54.1"},"reference-count":52,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002457","name":"Chosun University, in 2022","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002457","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3318322","type":"journal-article","created":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T17:56:56Z","timestamp":1695405416000},"page":"105379-105393","source":"Crossref","is-referenced-by-count":6,"title":["SELD U-Net: Joint Optimization of Sound Event Localization and Detection With Noise Reduction"],"prefix":"10.1109","volume":"11","author":[{"given":"Yeongseo","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Chosun University, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Guk","family":"Kim","sequence":"additional","affiliation":[{"name":"Maritime Research and Development Center, LIG Nex1, Seongnam, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Ho","family":"Choi","sequence":"additional","affiliation":[{"name":"Maritime Research and Development Center, LIG Nex1, Seongnam, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dae-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"Maritime Research and Development Center, LIG Nex1, Seongnam, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3361-8360","authenticated-orcid":false,"given":"Chanjun","family":"Chun","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Chosun University, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2012.6.1.40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s17040854"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2018.05.010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.966097"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231681"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015047"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2091502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905617"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521403"},{"key":"ref47","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","article-title":"Wave-U-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"arXiv 1806 03185"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref44","article-title":"Improved speech enhancement with the wave-U-net","author":"macartney","year":"2018","journal-title":"arXiv 1811 11307"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3128374"},{"key":"ref49","first-page":"1","article-title":"Incorporating Nesterov momentum into Adam","author":"dozat","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref7","first-page":"1267","article-title":"Acoustic event detection in real life recordings","author":"mesaros","year":"2010","journal-title":"Proc 18th Eur Signal Process Conf"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2999388"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"},{"key":"ref6","first-page":"1","article-title":"Event detection in short duration audio using Gaussian mixture model and random forest classifier","author":"kumar","year":"2013","journal-title":"Proc 21st Eur Signal Process Conf (EUSIPCO)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048675"},{"key":"ref40","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Med Image Comput Comput -Assist Intervent (MICCAI)"},{"key":"ref35","first-page":"716","article-title":"SALSA-lite: A fast and effective feature for polyphonic sound event localization and detection with microphone arrays","author":"nguyen","year":"2022","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3173054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICINFA.2009.5205092"},{"key":"ref36","first-page":"1","article-title":"Noise reduction using modified phase spectra and Wiener filter","author":"dang","year":"2011","journal-title":"Proc IEEE Int Workshop Mach Learn Signal Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref33","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020","journal-title":"arXiv 2006 01919"},{"key":"ref32","first-page":"1","article-title":"Two-stage sound event localization and detection using intensity vector and generalized cross-correlation","author":"cao","year":"2019","journal-title":"Proc Detection Classification Acoustic Scenes Events (DCASE) Challenge"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307286"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2016.0041"},{"key":"ref38","first-page":"1","article-title":"Perceptually motivated pre-filter for speech enhancement using Kalman filtering","author":"wang","year":"2007","journal-title":"Proc Int Conf Info Commun Signal Process"},{"key":"ref24","first-page":"138","article-title":"Classification of spatial audio location and content using convolutional neural networks","author":"hirvonen","year":"2015","journal-title":"Proc Audio Eng Soc Conv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217063"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/89.709670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903121"},{"key":"ref22","first-page":"1317","article-title":"Two-source acoustic event detection and localization: Online implementation in a smart-room","author":"butko","year":"2011","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.4979851"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10261207.pdf?arnumber=10261207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:22:37Z","timestamp":1698085357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10261207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3318322","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}