{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:15Z","timestamp":1763191395266,"version":"3.45.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230980","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering"],"prefix":"10.1109","author":[{"given":"Jiarui","family":"Hai","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"}]},{"given":"Mounya","family":"Elhilali","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"issue":"4","key":"ref3","article-title":"Conformer-based sound event detection with semi-supervised learning and data augmentation","volume":"1","author":"Miyazaki","year":"2020","journal-title":"dim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054478"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-176"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref9","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"Xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28084"},{"article-title":"Effective data augmentation with diffusion models","year":"2023","author":"Trabucco","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890066"},{"article-title":"Synthio: Augmenting small-scale audio classification datasets with synthetic data","year":"2024","author":"Ghosh","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-1137"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-246"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888184"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SynData4GenAI.2024-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref24","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","author":"Fonseca","year":"2017","journal-title":"ISMIR"},{"article-title":"A multi-device dataset for urban acoustic scene classification","year":"2018","author":"Mesaros","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","year":"2021","author":"Meng","key":"ref31"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230980.pdf?arnumber=11230980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:19:23Z","timestamp":1763191163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230980","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}