{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T17:10:42Z","timestamp":1785777042690,"version":"3.56.0"},"reference-count":45,"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"}],"funder":[{"name":"FPI","award":["PRE2022-104808"],"award-info":[{"award-number":["PRE2022-104808"]}]},{"DOI":"10.13039\/501100004895","name":"European Social Fund Plus","doi-asserted-by":"publisher","award":["PID2021-125943OB-I00"],"award-info":[{"award-number":["PID2021-125943OB-I00"]}],"id":[{"id":"10.13039\/501100004895","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004895","name":"European Social Fund Plus","doi-asserted-by":"publisher","award":["MCIN\/AEI\/10.13039\/501100011033\/FEDER"],"award-info":[{"award-number":["MCIN\/AEI\/10.13039\/501100011033\/FEDER"]}],"id":[{"id":"10.13039\/501100004895","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UE from the Spanish Ministerio de Ciencia e Innovacion and Fondo Europeo de Desarrollo Regional"}],"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.2024.3444490","type":"journal-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:45:43Z","timestamp":1723743943000},"page":"3896-3907","source":"Crossref","is-referenced-by-count":11,"title":["Enhancing Conformer-Based Sound Event Detection Using Frequency Dynamic Convolutions and BEATs Audio Embeddings"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8519-0549","authenticated-orcid":false,"given":"Sara","family":"Barahona","sequence":"first","affiliation":[{"name":"AUDIAS Research Group, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3725-2522","authenticated-orcid":false,"given":"Diego","family":"de Benito-Gorr\u00f3n","sequence":"additional","affiliation":[{"name":"AUDIAS Research Group, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1159-6455","authenticated-orcid":false,"given":"Doroteo T.","family":"Toledano","sequence":"additional","affiliation":[{"name":"AUDIAS Research Group, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5998-1489","authenticated-orcid":false,"given":"Daniel","family":"Ramos","sequence":"additional","affiliation":[{"name":"AUDIAS Research Group, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13928"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0214168"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3020099"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095833"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/machines11020187"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref14","first-page":"100","article-title":"Conformer-based sound event detection with semi-supervised learning and data augmentation","volume-title":"Proc. Detection Classification Acoust. Scenes Events 2020 Workshop","author":"Miyazaki","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICKECS56523.2022.10060191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref18","article-title":"Heavily augmented sound event detection utilizing weak predictions","author":"Nam","year":"2021"},{"key":"ref19","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Chen","year":"2023"},{"key":"ref20","article-title":"Multi-resolution combination of CRNN and conformers for DCASE 2022 task 4","author":"de Benito-Gorron","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3088949"},{"key":"ref22","first-page":"65","article-title":"Multiple feature resolutions for different polyphonic sound detection score scenarios in DCASE 2021 task 4","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events 2021 Workshop","author":"de Benito-Gorron","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref26","article-title":"Understanding and improving transformer from a multi-particle dynamic system point of view","author":"Lu","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref29","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref32","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chiu","year":"2022"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref35","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref40","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":"ref41","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref43","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref44","first-page":"11","article-title":"Multi-resolution conformer for sound event detection: Analysis and optimization","volume-title":"Proc. 8th Detection Classification Acoust. Scenes Events 2023 Workshop","author":"Barahona","year":"2023"},{"key":"ref45","article-title":"Semi-supervised learning-based sound event detection using frequency dynamic convolution with large kernel attention for DCASE challenge 2023 task 4","author":"Kim","year":"2023"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10637738.pdf?arnumber=10637738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T07:55:43Z","timestamp":1725609343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10637738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3444490","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}