{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:12:28Z","timestamp":1776885148931,"version":"3.51.2"},"reference-count":26,"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\/icassp49660.2025.10889813","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["FAF-Filt: Frequency-aware Fourier Filter for Sound Event Detection"],"prefix":"10.1109","author":[{"given":"Siyu","family":"Sun","sequence":"first","affiliation":[{"name":"ByteDance China,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohuai","family":"Le","sequence":"additional","affiliation":[{"name":"ByteDance China,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuangqi","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance China,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianjun","family":"Xia","sequence":"additional","affiliation":[{"name":"ByteDance China,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanzeng","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance China,Beijing,China"}],"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":"10.33682\/006b-jx26"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448228"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP58668.2023.10180246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref6","article-title":"Omni-Dimensional Dynamic Convolution","author":"Li","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-65"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747421"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096306"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-216"},{"key":"ref12","article-title":"Frequency & Channel Attention for computationally efficient sound event detection","author":"Nam","year":"2023","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref13","article-title":"Mean Teacher Convolution System for DCASE 2018 Task 4","author":"Lu","year":"2018","journal-title":"Tech. Rep., DCASE 2018 Challenge"},{"key":"ref14","first-page":"4479","article-title":"Fast Fourier Convolution","volume":"33","author":"Chi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"980","article-title":"Global Filter Networks for Image Classification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-603"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095716"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054478"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref23","first-page":"2613","article-title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","volume-title":"Proc. Interspeech","author":"Park"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref25","first-page":"1291","article-title":"Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection","volume-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing","volume":"25","author":"\u00c7akir","year":"2017"},{"key":"ref26","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":"Neural Information Processing Systems"}],"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\/10889813.pdf?arnumber=10889813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:40Z","timestamp":1774416340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889813","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}