{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T17:23:29Z","timestamp":1786209809989,"version":"3.56.0"},"reference-count":130,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Maria de Maeztu Units of Excellence Programme","award":["MDM-2015-0502"],"award-info":[{"award-number":["MDM-2015-0502"]}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["688382"],"award-info":[{"award-number":["688382"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","award":["Faculty Research Award"],"award-info":[{"award-number":["Faculty Research Award"]}],"id":[{"id":"10.13039\/100006785","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":[[2022]]},"DOI":"10.1109\/taslp.2021.3133208","type":"journal-article","created":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T21:12:34Z","timestamp":1639084354000},"page":"829-852","source":"Crossref","is-referenced-by-count":368,"title":["FSD50K: An Open Dataset of Human-Labeled Sound Events"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9872-3917","authenticated-orcid":false,"given":"Eduardo","family":"Fonseca","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Favory","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9603-0869","authenticated-orcid":false,"given":"Jordi","family":"Pons","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederic","family":"Font","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-312"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053611"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103831"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3224204"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052908"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0214168"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.4988946"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690579"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.33682\/ne8s-1m78"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.026"},{"key":"ref15","first-page":"1267","article-title":"Acoustic event detection in real life recordings","volume-title":"Proc. IEEE 18th Eur. Signal Process. Conf.","author":"Mesaros","year":"2010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.33682\/j5zw-2t88"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref30","article-title":"VOICe: A sound event detection dataset for generalizable domain adaptation","author":"Gharib","year":"2019"},{"key":"ref31","first-page":"32","article-title":"The SINS database for detection of daily activities in a home environment using an acoustic sensor network","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2017 Workshop","author":"Dekkers","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683158"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.33682\/w13e-5v06"},{"key":"ref34","first-page":"16","article-title":"SONYC-UST-V2: An urban sound tagging dataset with spatiotemporal context","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2020 Workshop","author":"Cartwright","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","article-title":"WebVision database: Visual learning and understanding from web data","author":"Li","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2875349"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3006378"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6060041"},{"key":"ref45","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref46","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"},{"key":"ref47","article-title":"Are we done with ImageNet","author":"Beyer","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632739"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0162075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683063"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521336"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3029652"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref57","first-page":"80","article-title":"An open dataset for research on audio field recording archives: freefield1010","volume-title":"Proc. Audio Eng. Soc. Conf., 53rd Int. Conf., Semantic Audio","author":"Stowell","year":"2014"},{"key":"ref58","first-page":"69","article-title":"General-purpose tagging of Freesound audio with AudioSet labels: Task description, dataset, and baseline","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2018 Workshop","author":"Fonseca","year":"2018"},{"key":"ref59","first-page":"486","article-title":"Freesound Datasets: A platform for the creation of open audio datasets","volume-title":"Proc. 18th Int. Soc. Music Inf. Retrieval Conf.","author":"Fonseca"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054478"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414774"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3134664"},{"key":"ref65","article-title":"Loudness Normalisation and Permitted Maximum Level of Audio Signals","volume-title":"Eur. Broadcast. Union","volume":"128","year":"2014"},{"key":"ref66","first-page":"859","article-title":"Corpus annotation through crowdsourcing: Towards best practice guidelines","volume-title":"Proc. 9th Int. Conf. Lang. Resour. Eval.","author":"Sabou","year":"2014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.33682\/y8xs-0463"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.2001.943160"},{"key":"ref70","first-page":"594","article-title":"Song-level features and support vector machines for music classification","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Mandel","year":"2005"},{"issue":"15","key":"ref71","first-page":"4","article-title":"Album and artist effects for audio similarity at the scale of the web","volume":"15","author":"Flexer","year":"2009","journal-title":"Children"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23808-6_10"},{"key":"ref73","volume-title":"Knapsack Problems: Algorithms and Computer Implementations","author":"Toth","year":"1990"},{"key":"ref74","first-page":"447","article-title":"Facilitating the manual annotation of sounds when using large taxonomies","volume-title":"Proc. 23rd Conf. Open Innov. Assoc.","author":"Favory","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901732"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref77","article-title":"A closer look at weak label learning for audio events","author":"Shah","year":"2018"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053160"},{"key":"ref79","first-page":"123","article-title":"Data-efficient weakly supervised learning for low-resource audio event detection using deep learning","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2018 Workshop","author":"Morfi","year":"2018"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169985"},{"key":"ref81","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2017 Workshop","author":"Mesaros","year":"2017"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-519"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946968"},{"key":"ref87","article-title":"Improving sound event classification by increasing shift invariance in convolutional neural networks","author":"Fonseca","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727634"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2975422"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937249"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"},{"key":"ref92","article-title":"COALA: Co-aligned autoencoders for learning semantically enriched audio representations","volume-title":"Proc. Workshop Self-Supervis. Audio Speech at 37th Int. Conf. Mach. Learn.","author":"Favory","year":"2020"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053065"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682341"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966293"},{"key":"ref96","first-page":"138","article-title":"Unsupervised adversarial domain adaptation for acoustic scene classification","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2018 Workshop","author":"Gharib","year":"2018"},{"key":"ref97","first-page":"379","article-title":"Cross-collection evaluation for music classification tasks","volume-title":"Proc. 17th Int. Soc. Music Inf. Retrieval Conf.","author":"Bogdanov","year":"2016"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390691"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref100","article-title":"USM-SED: A dataset for polyphonic sound event detection in urban sound monitoring scenarios","author":"Abeer","year":"2021"},{"key":"ref101","first-page":"205","article-title":"Improving sound event detection in domestic environments using sound separation","volume-title":"Proc. Detection Classification Acoustic Scenes Events 2020 Workshop (DCASE2020)","author":"Turpault","year":"2020"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74200-5_19"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref105","article-title":"Scikit-learn documentation 0.23.2. Precision-recall"},{"key":"ref106","article-title":"Metrics and scoring: quantifying the quality of predictions"},{"key":"ref107","article-title":"Plotting AP and ROC curves","author":"VLFeat"},{"key":"ref108","volume-title":"Signal Detection Theory and Psychophysics","volume":"1","author":"Green","year":"1966"},{"key":"ref109","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"ref110","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref113","first-page":"37","article-title":"Acoustic scene classification by ensembling gradient boosting machine and convolutional neural networks","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2017 Workshop","author":"Fonseca","year":"2017"},{"key":"ref114","first-page":"265","article-title":"A simple fusion of deep and shallow learning for acoustic scene classification","volume-title":"Proc. 15th Sound Music Comput. Conf.","author":"Fonseca","year":"2018"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.33682\/v1za-0k45"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.33682\/57xx-t679"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref118","first-page":"178","article-title":"Training general-purpose audio tagging networks with noisy labels and iterative self-verification","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2018 Workshop","author":"Dorfer","year":"2018"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937213"},{"key":"ref120","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054444"},{"key":"ref124","article-title":"Evaluation of CNN-based automatic music tagging models","volume-title":"Proc. 17th Sound Music Comput. Conf.","author":"Won","year":"2020"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2731"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014056429969"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1186\/1756-0500-4-267"},{"key":"ref129","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2018 Workshop","author":"Mesaros","year":"2018"},{"key":"ref130","article-title":"Knowledge concentration: Learning 100k object classifiers in a single CNN","author":"Gao","year":"2017"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09645159.pdf?arnumber=9645159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:59:52Z","timestamp":1709326792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9645159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":130,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3133208","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}