{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T02:47:00Z","timestamp":1792205220563,"version":"4.4.0"},"reference-count":74,"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\/4.0\/legalcode"}],"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.2024.3376984","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:17:37Z","timestamp":1710793057000},"page":"2227-2241","source":"Crossref","is-referenced-by-count":30,"title":["Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4988-6067","authenticated-orcid":false,"given":"Florian","family":"Schmid","sequence":"first","affiliation":[{"name":"Institute of Computational Perception (CP-JKU), Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-732X","authenticated-orcid":false,"given":"Khaled","family":"Koutini","sequence":"additional","affiliation":[{"name":"LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3531-1282","authenticated-orcid":false,"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[{"name":"LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref6","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref8","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ba","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096110"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289815"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref18","first-page":"1305","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/DCAS.2018.8620116"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00194"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref22","article-title":"BAM: Bottleneck attention module","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Park","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00318"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref25","first-page":"438","article-title":"OpenMIC-2018: An open data-set for multiple instrument recognition","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Humphrey","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref27","first-page":"56","article-title":"Acoustic scene classification in DCASE 2020 challenge: Generalization across devices and low complexity solutions","volume-title":"Proc. Workshop Detection Classification Acoustic Scenes Events","author":"Heittola","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref29","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref30","first-page":"6105","article-title":"Efficient Net:Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref31","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref34","article-title":"Searching for activation functions","volume-title":"Proc. Int. Conf. Learn. Representations Workshop Track","author":"Ramachandran","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00293"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref38","article-title":"CMKD: CNN\/transformer-based cross-model knowledge distillation for audio classification","author":"Gong","year":"2022"},{"key":"ref39","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref41","article-title":"DyNet: Dynamic convolution for accelerating convolutional neural networks","author":"Zhang","year":"2020"},{"key":"ref42","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299117"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747421"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1210"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1186"},{"key":"ref48","first-page":"1319","article-title":"Maxout networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goodfellow","year":"2013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref51","first-page":"171","article-title":"Description and analysis of novelties introduced in DCASE task 4 2022 on the baseline system","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Ronchini","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref53","first-page":"216","article-title":"Language-based audio retrieval task in DCASE 2022 challenge","volume-title":"Proc. Workshop Detection Classification Acoustic Scenes Events","author":"Xie","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/s21227665"},{"key":"ref55","first-page":"196","article-title":"Event classification with class-level gated unit using large-scale pretrained model for optical fiber sensing","volume-title":"Proc. Workshop Detection Classification Acoust. Scenes Events","author":"Tonami","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.07.012"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref58","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref59","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446348"},{"key":"ref62","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1564"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref68","article-title":"End-to-end audio strikes back: Boosting augmentations towards an efficient audio classification network","author":"Gazneli","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082307"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref71","article-title":"ONE-PEACE: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"ref72","article-title":"Designing acoustic scene classification models with CNN variants","author":"Suh","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289983"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10472152.pdf?arnumber=10472152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T18:24:41Z","timestamp":1712773481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3376984","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}