{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:56Z","timestamp":1774420196508,"version":"3.50.1"},"reference-count":40,"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\/icassp49660.2025.10888414","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Formula-Supervised Sound Event Detection: Pre-Training Without Real Data"],"prefix":"10.1109","author":[{"given":"Yuto","family":"Shibata","sequence":"first","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keitaro","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshiaki","family":"Bando","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Imoto","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokatsu","family":"Kalaoka","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshimitsu","family":"Aoki","sequence":"additional","affiliation":[{"name":"Keio University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref5","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref8","first-page":"19","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","volume-title":"Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Serizel"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096853"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"ref13","article-title":"Semi-supervsied learning-based sound event detection using freuqency dynamic convolution with large kernel attention for dcase challenge 2023 task 4","author":"Kim","year":"2023"},{"key":"ref14","article-title":"Dcase 2023 challenge task4 technical report","author":"Chen","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3108063"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3379503.3403551"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447130"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20094"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02055"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00247"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01835"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_9"},{"key":"ref25","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Engel"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/3680788"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-32576-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/2981562.2981582"},{"key":"ref29","volume-title":"Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023)","author":"Fuentes"},{"key":"ref30","article-title":"Pre-training and self-training for sound event detection in domestic environments","author":"Ebbers","year":"2022"},{"key":"ref31","article-title":"Self-trained audio tagging and sound event detection in domestic environments","volume-title":"Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)","author":"Ebbers"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.31219\/osf.io\/m5eba","article-title":"Forward-backward convolutional recurrent neural networks and tag-conditioned convolutional neural networks for weakly labeled semi-supervised sound event detection","author":"Ebbers","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref36","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref40","first-page":"1","article-title":"A database and challenge for acoustic scene classification and event detection","volume-title":"21st European Signal Processing Conference (EUSIPCO 2013)","author":"Giannoulis"}],"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\/10888414.pdf?arnumber=10888414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:58Z","timestamp":1774416418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888414","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}