{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T18:50:44Z","timestamp":1776365444108,"version":"3.51.2"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N014111\/1"],"award-info":[{"award-number":["EP\/N014111\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201406150082"],"award-info":[{"award-number":["201406150082"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EPSRC Doctoral Training Partnership","award":["EP\/N509772\/1"],"award-info":[{"award-number":["EP\/N509772\/1"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11804365"],"award-info":[{"award-number":["11804365"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201406150082"],"award-info":[{"award-number":["201406150082"]}],"id":[{"id":"10.13039\/501100004543","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":[[2020]]},"DOI":"10.1109\/taslp.2020.3030497","type":"journal-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T18:12:50Z","timestamp":1603303970000},"page":"2880-2894","source":"Crossref","is-referenced-by-count":918,"title":["PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2864-0475","authenticated-orcid":false,"given":"Qiuqiang","family":"Kong","sequence":"first","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}]},{"given":"Yin","family":"Cao","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3393-2544","authenticated-orcid":false,"given":"Turab","family":"Iqbal","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-1075","authenticated-orcid":false,"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}]}],"member":"263","reference":[{"key":"ref39","article-title":"Network in network","author":"lin","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref33","year":"0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref30","first-page":"3511","article-title":"Non-speech environmental sound classification using SVMs with a new set of features","volume":"8","author":"uzkent","year":"2012","journal-title":"Int J Innovative Comput Inform Control"},{"key":"ref37","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref28","article-title":"An MFCC-GMM approach for event detection and classification","author":"vuegen","year":"0","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(00)00119-7"},{"key":"ref29","first-page":"1267","article-title":"Acoust. event detection in real life recordings","author":"mesaros","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref2","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref22","article-title":"Polyphonic sound event detection with weak labeling","author":"wang","year":"2018"},{"key":"ref21","first-page":"29","article-title":"Transfer learning by supervised pre-training for audio-based music classification","author":"van den oord","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518881"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169984"},{"key":"ref25","author":"pons","year":"2019","journal-title":"arXiv 1909 06654"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref51","year":"0"},{"key":"ref59","first-page":"1459","article-title":"RAVDESS: The Ryerson audio-visual database of emotional speech and song","author":"livingstone","year":"0","journal-title":"Proc Annu Meet Can Soc Brain Behav Cognitive Sci"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5539-3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref56","article-title":"Bottom-up broadcast neural network for music genre classification","author":"liu","year":"2019","journal-title":"arXiv 1901 08928"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683292"},{"key":"ref54","first-page":"69","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline","author":"fonseca","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref53","year":"0"},{"key":"ref52","year":"0"},{"key":"ref10","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref40","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref12","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref14","first-page":"141","article-title":"Transfer learning for music classification and regression tasks","author":"choi","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref15","first-page":"637","article-title":"End-to-end learning for music audio tagging at scale","author":"pons","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"ref17","first-page":"188","article-title":"Multi-level attention model for weakly supervised audio classification","author":"yu","year":"0","journal-title":"Proc Workshop Detection Classif Acoust Scenes Events"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/463"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref3","first-page":"805","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref6","year":"0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/78.143457"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-831"},{"key":"ref9","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2731"},{"key":"ref47","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","first-page":"220","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","author":"lee","year":"0","journal-title":"Proc Sound and Music Computing Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref44","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09229505.pdf?arnumber=9229505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:45:12Z","timestamp":1706553912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9229505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3030497","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}