{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:52Z","timestamp":1774419712444,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888080","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Unified Audio Event Detection"],"prefix":"10.1109","author":[{"given":"Yidi","family":"Jiang","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Tao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889789"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1228"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094752"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref8","article-title":"Flow-tsvad: Targetspeaker voice activity detection via latent flow matching","author":"Chen","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888389"},{"key":"ref10","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref13","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446072"},{"key":"ref17","article-title":"Target speech diarization with multimodal prompts","author":"Jiang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2158419"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096853"},{"key":"ref27","article-title":"Label filtering-based self-learning for sound event detection using frequency dynamic convolution with large kernel attention","volume-title":"Proc. DCASE","author":"Kim"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3366756"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref32","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888080.pdf?arnumber=10888080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:15Z","timestamp":1774416255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888080","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}