{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:28:28Z","timestamp":1781713708148,"version":"3.54.5"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249270","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"143-148","source":"Crossref","is-referenced-by-count":5,"title":["DG-SED: Domain Generalization for Sound Event Detection with Heterogeneous Training Data"],"prefix":"10.1109","author":[{"given":"Yang","family":"Xiao","sequence":"first","affiliation":[{"name":"Fortemedia Singapore,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Yin","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jisheng","family":"Bai","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[{"name":"Fortemedia Singapore,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"ref4","volume-title":"FMSG submission for DCASE 2023 challenge task 4 on sound event detection with weak labels and synthetic soundscapes","author":"Xiao","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-909"},{"key":"ref7","volume-title":"FMSGJLESS submission for DCASE 2024 task4 on sound event detection with heterogeneous training dataset and potentially missing labels","author":"Xiao","year":"2024"},{"key":"ref8","article-title":"DCASE 2024 task 4: Sound event detection with heterogeneous data and missing labels","volume-title":"Proc. the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)","author":"Cornell","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233468"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11209062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889789"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-61"},{"key":"ref16","article-title":"Batch-instance normalization for adaptively style-invariant neural networks","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","volume":"31","author":"Nam","year":"2018"},{"key":"ref17","article-title":"WildDESED: An LLMpowered dataset for wild domestic environment sound event detection system","volume-title":"Proc. the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)","author":"Xiao","year":"2024"},{"key":"ref18","article-title":"USTC-NELSIP system for dcase 2018 challenge task 4","author":"Liu","year":"2018","journal-title":"DCASE2018 Challenge"},{"key":"ref19","first-page":"230","article-title":"Two-stage domain adaptation for sound event detection","volume-title":"Proc. the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)","author":"Yang","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937231"},{"key":"ref21","article-title":"Domain generalization with mixstyle","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Zhou","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2075"},{"key":"ref24","article-title":"Description and analysis of novelties introduced in DCASE task 42022 on the baseline system","author":"Ronchini","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"5178","article-title":"BEATs: Audio pretraining with acoustic tokenizers","volume-title":"Proc. International conference on machine learning (ICML)","volume":"202","author":"Chen","year":"2023"},{"key":"ref26","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref27","volume-title":"Mean teacher convolution system for DCASE 2018 task 4","author":"JiaKai","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref30","first-page":"1120","article-title":"Learning whom to trust with MACE","volume-title":"Proc. NAACL","author":"Hovy","year":"2013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref32","volume-title":"Semi-supervised sound event detection based on pretrained models for DCASE 2024 task 4","author":"Chen","year":"2024"},{"key":"ref33","volume-title":"Sound event detection based on auxiliary decoder and maximum probability aggregation for DCASE challenge 2024 task 4","author":"Son","year":"2024"},{"key":"ref34","volume-title":"Local and global features fusion for sound event detection with heterogeneous training dataset and potentially missing labels","author":"Yue","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref36","article-title":"Postprocessing independent evaluation of sound event detection systems","volume-title":"Proc. the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)","author":"Ebbers","year":"2023"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Singapore, Singapore","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249270.pdf?arnumber=11249270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:57:31Z","timestamp":1764399451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249270","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}