{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:32:03Z","timestamp":1774539123197,"version":"3.50.1"},"reference-count":58,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011878","name":"Vlaamse regering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen"}],"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.2023.3323135","type":"journal-article","created":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:24:39Z","timestamp":1696879479000},"page":"68-82","source":"Crossref","is-referenced-by-count":11,"title":["Cooperative Scene-Event Modelling for Acoustic Scene Classification"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8469-5740","authenticated-orcid":false,"given":"Yuanbo","family":"Hou","sequence":"first","affiliation":[{"name":"WAVES Research Group, Ghent University, Gent, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9895-9927","authenticated-orcid":false,"given":"Bo","family":"Kang","sequence":"additional","affiliation":[{"name":"IDLab, Ghent University, Gent, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0978-5046","authenticated-orcid":false,"given":"Andrew","family":"Mitchell","sequence":"additional","affiliation":[{"name":"Institute for Environmental Design and Engineering, The Bartlett, University College London, London, U.K."}]},{"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\/0000-0001-8995-5636","authenticated-orcid":false,"given":"Jian","family":"Kang","sequence":"additional","affiliation":[{"name":"Institute for Environmental Design and Engineering, The Bartlett, University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7756-7238","authenticated-orcid":false,"given":"Dick","family":"Botteldooren","sequence":"additional","affiliation":[{"name":"WAVES Research Group, Ghent University, Gent, Belgium"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2017.08.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-37"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1201\/b19145-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2169"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7036"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053702"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892893"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937196"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref14","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Ba","year":"2014"},{"key":"ref15","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","volume-title":"Proc. DCASE","author":"Mesaros","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref18","first-page":"78","article-title":"Polyphonic audio tagging with sequentially labelled data using crnn with learnable gated linear units","volume-title":"Proc. DCASE","author":"Hou","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683627"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00074"},{"key":"ref21","first-page":"1","article-title":"Acoustic scene classification using convolutional recurrent neural networks","author":"Jallet","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1806"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00136"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3837\/tiis.2018.06.017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref30","article-title":"TAU urban acoustic scenes 2019, development dataset","author":"Heittola","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096842"},{"key":"ref32","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref33","first-page":"217","article-title":"DCASE 2018 challenge surrey cross-task convolutional neural network baseline","volume-title":"Proc. DCASE","author":"Kong","year":"2018"},{"issue":"1","key":"ref34","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2018.12.016"},{"key":"ref36","first-page":"313","article-title":"AUC optimization vs. error rate minimization","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"16","author":"Cortes","year":"2003"},{"key":"ref37","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/305"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240523"},{"key":"ref40","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2909737"},{"key":"ref42","first-page":"284","article-title":"Sigsoftmax: Reanalysis of the softmax bottleneck","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kanai","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/cyto.a.20896"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/e19110631"},{"key":"ref46","first-page":"23","article-title":"Acoustic scene classification using convolutional neural networks and different channels representations and its fusion","author":"Golubkov","year":"2018"},{"key":"ref47","first-page":"29","article-title":"Acoustic scene classification using multi-scale features","author":"Yang","year":"2018"},{"key":"ref48","first-page":"103","article-title":"Exploring deep vision models for acoustic scene classification","author":"Mariotti","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2023.3319233"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref53","first-page":"93","article-title":"Sample mixed-based data augmentation for domestic audio tagging","volume-title":"Proc. DCASE","author":"Wei","year":"2018"},{"key":"ref54","first-page":"1","article-title":"The system for acoustic scene classification using resnet","author":"Liu","year":"2019"},{"key":"ref55","first-page":"1","article-title":"Acoustic scene classification based on binaural deep scattering spectra with neural network","author":"Ma","year":"2019"},{"key":"ref56","first-page":"1","article-title":"Acoustic scene classification using fusion of attentive convolutional neural networks for DCASE2019 challenge","author":"Zeinali","year":"2019"},{"key":"ref57","first-page":"22","article-title":"Deep neural networks with supported clusters preclassification procedure for acoustic scene recognition","author":"Plata","year":"2019"},{"key":"ref58","first-page":"1","article-title":"Acoustic scene classification based on the dataset with deep convolutional generated against network","author":"Ning","year":"2019"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10274856.pdf?arnumber=10274856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:52:36Z","timestamp":1712904756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10274856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3323135","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}