{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:01:33Z","timestamp":1781366493853,"version":"3.54.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446159","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"911-915","source":"Crossref","is-referenced-by-count":29,"title":["Fine-Tune the Pretrained ATST Model for Sound Event Detection"],"prefix":"10.1109","author":[{"given":"Nian","family":"Shao","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref4","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 (NIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/504"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10037"},{"key":"ref8","article-title":"Mean teacher convolution system for dcase 2018 task 4","volume-title":"Tech. Rep., DCASE2018 Challenge","author":"JiaKai","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414931"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"International Conference on Machine Learning (ICML)","author":"Chen"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref14","article-title":"Sound event detection with weak prediction for dcase 2023 challenge task4a","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Xiao","year":"2023"},{"key":"ref15","article-title":"Semi-supervised learning-based sound event detection using frequency dynamic convolution with large kernel attention for DCASE challenge 2023 task 4","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Kim","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10126"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3352248"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref19","first-page":"2579","article-title":"Visualizing data using t-sne","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref22","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations (ICLR)","author":"Bao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096853"},{"key":"ref24","article-title":"Li USTC team\u2019s submission for DCASE 2023 challenge task4a","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446159.pdf?arnumber=10446159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T17:49:10Z","timestamp":1748454550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446159","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}