{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:14:10Z","timestamp":1792080850081,"version":"4.4.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Austrian federal government and the Federal State of Upper Austria"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3082307","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T16:04:02Z","timestamp":1621872242000},"page":"1987-2000","source":"Crossref","is-referenced-by-count":47,"title":["Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-732X","authenticated-orcid":false,"given":"Khaled","family":"Koutini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0773-5651","authenticated-orcid":false,"given":"Hamid","family":"Eghbal-zadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3531-1282","authenticated-orcid":false,"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"83","article-title":"An attention mechanism for musical instrument recognition","author":"gururani","year":"0","journal-title":"Proc 20th Int Soc Music Inf Retrieval Conf"},{"key":"ref38","first-page":"438","article-title":"Openmic-2018: An open data-set for multiple instrument recognition","author":"humphrey","year":"0","journal-title":"Proc 19th Int Soc Music Inf Retrieval Conf"},{"key":"ref33","article-title":"Emotion and themes recognition in music utilising convolutional and recurrent neural networks","volume":"12","author":"amiriparian","year":"0","journal-title":"Proc Work Notes MediaEval Workshop ceur-ws org"},{"key":"ref32","article-title":"Music theme recognition using cnn and self-attention","volume":"12","author":"sukhavasi","year":"0","journal-title":"Proc Work Notes Proc MediaEval Workshop ceur-ws org"},{"key":"ref31","article-title":"Emotion and theme recognition in music with frequency-aware RF-Regularized CNNs","volume":"12","author":"koutini","year":"0","journal-title":"Proc Work Notes MediaEval Workshop"},{"key":"ref30","article-title":"The MTG-Jamendo dataset for automatic music tagging","author":"bogdanov","year":"0","journal-title":"Proc Mach Learn Music Discov Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref62","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00021","article-title":"Computing receptive fields of convolutional neural networks","author":"araujo","year":"2019","journal-title":"Distillation"},{"key":"ref63","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2014.01.011"},{"key":"ref64","article-title":"Shake-shake regularization of 3-branch residual networks","author":"gastaldi","year":"0","journal-title":"International Conference on Learning Representations Workshops Track"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nn0810-913"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2016.7500246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"ref20","article-title":"Classifying short acoustic scenes with I-vectors and CNNs: Challenges and optimisations for the 2017 DCASE ASC task","author":"lehner","year":"0","journal-title":"Dcase2016 challenge"},{"key":"ref22","article-title":"Acoustic scene classification by ensemble of spectrograms based on adaptive temporal divisions","author":"sakashita","year":"0","journal-title":"DCASE2018 Challenge"},{"key":"ref21","article-title":"Acoustic scene classification with fully convolutional neural networks and I-vectors","author":"dorfer","year":"0","journal-title":"DCASE2018 Challenge"},{"key":"ref24","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"},{"key":"ref23","article-title":"ADSC submission for DCASE 2017: Acoustic scene classification using deep residual convolutional neural networks","author":"zhao","year":"0","journal-title":"Dcase2016 challenge"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2007.07.011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2481179"},{"key":"ref50","article-title":"Acoustic scene classification using various pre-processed features and convolutional neural networks","author":"hyeji","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref51","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier gans","volume":"70","author":"odena","year":"0","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.33682\/cjd9-kc43"},{"key":"ref58","article-title":"Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref56","article-title":"Deep double descent: Where bigger models and more data hurt","author":"nakkiran","year":"0","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref55","first-page":"6105","article-title":"Rethinking model scaling for convolutional neural networks","author":"tan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053625"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902732"},{"key":"ref52","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref11","article-title":"CP-JKU submissions for DCASE-2016: A hybrid approach using binaural I-vectors and deep convolutional neural networks,” DCASE2016 challenge","author":"eghbal-zadeh","year":"0"},{"key":"ref40","article-title":"Learning multi-instrument classification with partial labels","author":"kenarsari-anhari","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref13","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"luo","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.33682\/v9qj-8954"},{"key":"ref15","article-title":"CP-JKU submissions to DCASE’19: Acoustic scene classification and audio tagging with receptive-field-regularized CNNs,” DCASE2019 challenge","author":"koutini","year":"2019","journal-title":"Tech Rep"},{"key":"ref16","article-title":"Designing acoustic scene classification models with CNN variants,” DCASE2020 challenge","author":"suh","year":"2020","journal-title":"Tech Rep"},{"key":"ref17","article-title":"CP-JKU submissions to Dcase’20: Low-complexity cross-device acoustic scene classification with RF-Regularized CNNs,” DCASE2020 challenge","author":"koutini","year":"2020","journal-title":"Tech Rep"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.33682\/w13e-5v06"},{"key":"ref19","article-title":"Acoustic scene classification with reject option based on ResNets","author":"lehner","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577348"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref46","first-page":"569","article-title":"Instrument activity detection in polyphonic music using deep neural networks","author":"gururani","year":"0","journal-title":"Proc 19th Int Soc Music Inf Retrieval Conf"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3273024.3273036"},{"key":"ref48","first-page":"316","article-title":"FMA: A dataset for music analysis","author":"defferrard","year":"0","journal-title":"Proc 18th Int Soc Music Inf Retrieval Conf"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.4946988"},{"key":"ref42","article-title":"Integrating the data augmentation scheme with various classifiers for acoustic scene modeling","author":"chen","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref43","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09439825.pdf?arnumber=9439825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:53:59Z","timestamp":1652180039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9439825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3082307","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}