{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:09Z","timestamp":1774420149618,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890706","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["No Class Left Behind: A Closer Look at Class Balancing for Audio Tagging"],"prefix":"10.1109","author":[{"given":"Janek","family":"Ebbers","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois G.","family":"Germain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Wilkinghoff","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref5","first-page":"5178","article-title":"BEATs: audio pre-training with acoustic tokenizers","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096110"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446348"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_29"},{"key":"ref13","article-title":"Solution for large-scale hierarchical object detection datasets with incomplete annotation and data imbalance","author":"Gao","year":"2018"},{"key":"ref14","article-title":"WaveBeat: End-to-end beat and downbeat tracking in the time domain","author":"Steinmetz","year":"2021","journal-title":"Audio Engineering Society Convention 151"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3013105"},{"key":"ref16","first-page":"197","article-title":"Audio tagging system using densely connected convolutional networks","volume-title":"Proc. DCASE","author":"Jeong"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref20","first-page":"28 708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","author":"Niizumi","year":"2022","journal-title":"HEAR: Holistic Evaluation of Audio Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/421"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref25","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"ref26","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref28","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref29","article-title":"Pre-training and self-training for sound event detection in domestic environments","volume-title":"Proc. DCASE","author":"Ebbers"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095938"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445834"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890706.pdf?arnumber=10890706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:41Z","timestamp":1774416401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890706","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}