{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:28:44Z","timestamp":1776356924475,"version":"3.51.2"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"21","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005049","name":"National Science and Engineering Research Council of Canada (NSERC) via their Alliance program","doi-asserted-by":"publisher","award":["ALLRP 548872-19"],"award-info":[{"award-number":["ALLRP 548872-19"]}],"id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,11,1]]},"DOI":"10.1109\/jiot.2025.3599483","type":"journal-article","created":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T18:22:26Z","timestamp":1755282146000},"page":"45000-45010","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking Self-Supervised Audio Representations for IoT-Enabled Acoustic Beehive Monitoring"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9929-9871","authenticated-orcid":false,"given":"Heitor R.","family":"Guimar\u00e3es","sequence":"first","affiliation":[{"name":"Énergie Matériaux Télécommunications Research Centre, Institut National de la Recherche Scientifique (INRS - EMT), Montréal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-0101","authenticated-orcid":false,"given":"Mahsa","family":"Abdollahi","sequence":"additional","affiliation":[{"name":"Énergie Matériaux Télécommunications Research Centre, Institut National de la Recherche Scientifique (INRS - EMT), Montréal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7413-5205","authenticated-orcid":false,"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Énergie Matériaux Télécommunications Research Centre, Institut National de la Recherche Scientifique (INRS - EMT), Montréal, QC, Canada"}]},{"given":"S\u00e9gol\u00e8ne","family":"Maucourt","sequence":"additional","affiliation":[{"name":"Département de biologie, Université Laval, Laval, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1798-4661","authenticated-orcid":false,"given":"Nicolas","family":"Coallier","sequence":"additional","affiliation":[{"name":"Nectar Technologies Inc., Montréal, QC, Canada"}]},{"given":"Pierre","family":"Giovenazzo","sequence":"additional","affiliation":[{"name":"Département de biologie, Université Laval, Laval, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5739-2514","authenticated-orcid":false,"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[{"name":"Énergie Matériaux Télécommunications Research Centre, Institut National de la Recherche Scientifique (INRS - EMT), Montréal, QC, Canada"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Good Beekeeping Practices for Sustainable Apiculture","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CIMCA.2018.8739710"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117104"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2021.101246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009426"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3221007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446409"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46338-9_5"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1101\/2022.10.12.511740","volume-title":"Bioacoustic event detection with self-supervised contrastive learning","author":"Bermant","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MetroAgriFor58484.2023.10424387"},{"key":"ref12","article-title":"Semi-supervised audio representation learning for modeling beehive strengths","author":"Zhang","year":"2021","journal-title":"arXiv:2105.10536"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski"},{"key":"ref15","first-page":"125","article-title":"Hear: Holistic evaluation of audio representations","volume-title":"Proc. NeurIPS Competit. Demonstrat. Track","author":"Turian"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889684"},{"key":"ref17","first-page":"929","article-title":"PyTorch 2: Faster machine learning through dynamic python bytecode transformation and graph compilation","volume-title":"Proc. 29th ACM Int. Conf. Archit. Support Program. Lang. Oper. Syst. (ASPLOS)","author":"Ansel"},{"key":"ref18","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv:2106.04624"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"ref21","first-page":"1","article-title":"Generative pre-training for speech with flow matching","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00649"},{"key":"ref24","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app12083920"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/09712119.2005.9706535"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2008.05.010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.02.024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IE51775.2021.9486575"},{"key":"ref30","volume-title":"A Preliminary Study of Sounds Emitted by Honey Bees in a Beehive","author":"Cecchi","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682981"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"issue":"8","key":"ref33","first-page":"2","article-title":"Neural networks for machine learning lecture 6A overview of mini-batch gradient descent","volume":"14","author":"Hinton","year":"2012","journal-title":"Cited"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/app13010195"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-04869-1"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"issue":"10","key":"ref38","doi-asserted-by":"crossref","first-page":"4632","DOI":"10.3390\/app11104632","article-title":"Audio, image, video, and weather datasets for continuous electronic beehive monitoring","volume":"11","author":"Kulyukin","year":"2021","journal-title":"Appl. Sci."},{"key":"ref39","article-title":"Automation of feature selection and generation of optimal feature subsets for beehive audio sample classification","author":"Bhouraskar","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE58730.2023.10289037"},{"key":"ref41","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022770"},{"key":"ref43","first-page":"1","article-title":"Masked modeling duo: Learning representations by encouraging both networks to model the input","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP)","author":"Niizumi"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn52387.2021.9534474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref50","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref51","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","volume-title":"Proc. Mach. Learn. Res.","author":"Niizumi"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"2391","DOI":"10.1109\/TASLP.2024.3389636","article-title":"Masked modeling duo: Towards a universal audio pre-training framework","volume":"32","author":"Niizumi","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"ref53","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref54","first-page":"1","article-title":"Contrastive audio-visual masked autoencoder","volume-title":"Proc. 11th Int. Conf. Learn. Represen.","author":"Gong"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095642"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ELEKTRO.2018.8398253"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ET50336.2020.9238260"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36810-0"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1080\/09524622.2016.1190946"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-66115-5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/BF00603817"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1213"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095480"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096445"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11217273\/11126110.pdf?arnumber=11126110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:09:58Z","timestamp":1771362598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11126110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"references-count":65,"journal-issue":{"issue":"21"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3599483","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]}}}