{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:41:19Z","timestamp":1776879679152,"version":"3.51.2"},"reference-count":25,"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"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230981","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":1,"title":["Sound event detection with audio-text models and heterogeneous temporal annotations"],"prefix":"10.1109","author":[{"given":"Manu","family":"Harju","sequence":"first","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Annamaria","family":"Mesaros","sequence":"additional","affiliation":[{"name":"Tampere University,Signal Processing Research Centre,Finland"}],"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":"10.1109\/ICASSP.2017.7952261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/TASLPRO.2025.3583354","article-title":"AudioSetCaps: Enriched audio captioning dataset generation using large audio language models","volume-title":"Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation","author":"Bai"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49660.2025.10889473","article-title":"Sound-VECaps: Improving audio generation with visual enhanced captions","volume-title":"Proc. ICASSP","author":"Yuan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887673"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref9","first-page":"31","article-title":"DCASE 2024 task 4: Sound event detection with heterogeneous data and missing labels","volume-title":"Proc. DCASE","author":"Cornell"},{"key":"ref10","first-page":"41","article-title":"Forward-backward convolutional recurrent neural networks and tag-conditioned convolutional neural networks for weakly labeled semi-supervised sound event detection","volume-title":"Proc. DCASE","author":"Ebbers"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715098"},{"key":"ref12","first-page":"200","article-title":"Training sound event detection on a heterogeneous dataset","volume-title":"Proc. DCASE","author":"Turpault"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1614"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747336"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3520017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT","author":"Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888942"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"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\/11230981.pdf?arnumber=11230981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:45:54Z","timestamp":1763192754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230981\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230981","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}