{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:30:32Z","timestamp":1784388632488,"version":"3.55.0"},"reference-count":81,"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":["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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3256088","type":"journal-article","created":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T17:43:58Z","timestamp":1678729438000},"page":"1251-1264","source":"Crossref","is-referenced-by-count":94,"title":["A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-3920","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, 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":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua-Xin","family":"Wu","sequence":"additional","affiliation":[{"name":"iFlytek, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFlytek, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Ma","sequence":"additional","affiliation":[{"name":"iFlytek, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599595"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref5","first-page":"1272","article-title":"Audio context recognition using audio event histograms","volume-title":"Proc. IEEE 18th Eur. Signal Process. Conf.","author":"Heittola","year":"2010"},{"key":"ref6","first-page":"1267","article-title":"Acoustic event detection in real life recordings","volume-title":"Proc. IEEE Eur. Signal Process. Conf.","author":"Mesaros","year":"2010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref17","first-page":"3856","article-title":"Dynamic routing between capsules","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sabour","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2902305"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659533"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/29.32276"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.2346089"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599651"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366631"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2018.2874430"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362645"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2736067"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054462"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2919378"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438544"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref38","first-page":"11","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"Perez","year":"2017","journal-title":"Convolutional Neural Netw. Vis. Recognit."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref40","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","volume-title":"Proc. Detect. Classification Acoust. Scenes Events Workshop","author":"Politis","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616168"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053298"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746544"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2990485"},{"key":"ref45","first-page":"125","article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","volume-title":"Proc. Detect. Classification Acoust. Scenes Events Workshop","author":"Politis","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746872"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref48","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","year":"2018"},{"key":"ref49","article-title":"Bidirectional GRU for sound event detection","author":"Lu","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-805"},{"key":"ref51","article-title":"Sound event localization and detection using activity-coupled cartesian DOA vector and RD3Net","volume-title":"DCASE2020 Challenge","author":"Shimada","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060257"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898454"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref57","article-title":"Data augmentation and prior knowledge-based regularization for sound event localization and detection","author":"Zhang","year":"2019"},{"key":"ref58","article-title":"The USTC-iFlytek system for sound event localization and detection of DCASE2020 challenge","author":"Wang","year":"2020"},{"key":"ref59","article-title":"Sound event localization and detection challenge results","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref61","article-title":"The NERC-SLIP system for sound event localization and detection of DCASE2022 challenge","author":"Wang","year":"2022"},{"key":"ref62","article-title":"Sound event localization and detection challenge results","year":"2022"},{"key":"ref63","article-title":"Comparison of first-order ambisonics microphone arrays","volume-title":"Proc. Int. Conf. Spatial Audio","author":"Kurz","year":"2015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170028"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref66","first-page":"125","article-title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. Detection Classification Acoust. Scenes Events Workshop","author":"Politis","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596248"},{"key":"ref68","article-title":"EM32 eigenmike microphone array release notes","year":"2013"},{"key":"ref69","article-title":"Reprsentation de champs acoustiques, application  la transmission et  la reproduction de scnes sonores complexes dans un contexte multimdia","author":"Daniel","year":"2000"},{"key":"ref70","article-title":"Sound event localization and detection using FOA domain spatial augmentation","author":"Mazzon","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362116"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref78","article-title":"Convolution-augmented transformer for semi-supervised sound event detection","author":"Miyazaki","year":"2020"},{"key":"ref79","article-title":"Two-stage sound event localization and detection using intensity vector and generalized cross-correlation","author":"Cao","year":"2019"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref81","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10068271.pdf?arnumber=10068271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:05:18Z","timestamp":1707829518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10068271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3256088","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}