{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T20:49:43Z","timestamp":1781556583142,"version":"3.54.5"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2026.3698771","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:38:09Z","timestamp":1780342689000},"page":"2340-2344","source":"Crossref","is-referenced-by-count":0,"title":["Sound Event Detection With Boundary-Aware Optimization and Inference"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4988-6067","authenticated-orcid":false,"given":"Florian","family":"Schmid","sequence":"first","affiliation":[{"name":"Institute of Computational Perception, Johannes Kepler University Linz (JKU), Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi Ian","family":"Tang","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjeel","family":"Parekh","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vamsi Krishna","family":"Ithapu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Azcarreta","family":"Ortiz","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Ferroni","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijun","family":"Qian","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnoldas","family":"Jasonas","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cosmin","family":"Frateanu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9687-2066","authenticated-orcid":false,"given":"Camilla","family":"Clark","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3531-1282","authenticated-orcid":false,"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[{"name":"Institute of Computational Perception, Johannes Kepler University Linz (JKU), Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c7a\u011fda\u015f","family":"Bilen","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2503881"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2009.2030171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-63450-0","volume-title":"Computational Analysis of Sound Scenes and Events","volume":"9","author":"Virtanen","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1039470.1039478"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/app12073293"},{"key":"ref8","article-title":"Sound event detection transformer: An event-based end-to-end model for sound event detection","author":"Ye","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27837"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888942"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-714"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref13","first-page":"141","article-title":"Multi-iteration multi-stage fine-tuning of transformers for sound event detection with heterogeneous datasets","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Schmid","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref15","article-title":"A closer look at weak label learning for audio events","author":"Shah","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054433"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3509336"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68279-0_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref31","article-title":"Sound event detection","author":"Bilen","year":"2022"},{"key":"ref32","article-title":"Efficient parallelization of an ubiquitous sequential computation","author":"Heinsen","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref34","first-page":"31","article-title":"DCASE 2024 task 4: Sound event detection with heterogeneous data and missing labels","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Cornell","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3352248"},{"key":"ref36","first-page":"5178","article-title":"Beats: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Chen","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63237.2025.11226457"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-61"},{"key":"ref41","article-title":"Knowledge distillation from transformers for low-complexity acoustic scene classification","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop","author":"Schmid","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11540433.pdf?arnumber=11540433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:50:56Z","timestamp":1781553056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11540433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/lsp.2026.3698771","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}