{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T12:57:58Z","timestamp":1776171478223,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096853","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":24,"title":["AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer"],"prefix":"10.1109","author":[{"given":"Kang","family":"Li","sequence":"first","affiliation":[{"name":"University Of Science And Technology Of China,National Engineering Research Centre of Speech and Language Information Processing,Hefei,China"}]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[{"name":"University Of Science And Technology Of China,National Engineering Research Centre of Speech and Language Information Processing,Hefei,China"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[{"name":"University Of Science And Technology Of China,National Engineering Research Centre of Speech and Language Information Processing,Hefei,China"}]},{"given":"Ian","family":"McLoughlin","sequence":"additional","affiliation":[{"name":"University Of Science And Technology Of China,National Engineering Research Centre of Speech and Language Information Processing,Hefei,China"}]},{"given":"Xin","family":"Fang","sequence":"additional","affiliation":[{"name":"iFLYTEK Co. Ltd,iFLYTEK Research,Hefei,China"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"iFLYTEK Co. Ltd,iFLYTEK Research,Hefei,China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Pre-training and self-training for sound event detection in domestic environments","author":"ebbers","year":"2022","journal-title":"Tech Rep"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref14","article-title":"Pretrained models in sound event detection for dcase 2022 challenge task4","author":"xiao","year":"2022","journal-title":"Tech Rep"},{"key":"ref11","first-page":"100","article-title":"Convolution augmented transformer for semi-supervised sound event detection","author":"miyazaki","year":"2020","journal-title":"Proc Workshop Detection Classification Acoust Scenes Events (DCASE)"},{"key":"ref10","author":"nam","year":"2022","journal-title":"Frequency dynamic convolution Frequency-adaptive pattern recognition for sound event detection"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.4988686"},{"key":"ref17","author":"cho","year":"2014","journal-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref23","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref25","author":"loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref20","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414931"},{"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"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746878"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-281"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096853.pdf?arnumber=10096853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:58:45Z","timestamp":1700506725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096853","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}