{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:43:59Z","timestamp":1776887039912,"version":"3.51.2"},"reference-count":42,"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\/icassp49660.2025.10889789","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":13,"title":["Exploring Text-Queried Sound Event Detection with Audio Source Separation"],"prefix":"10.1109","author":[{"given":"Han","family":"Yin","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jisheng","family":"Bai","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Fortemedia,Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yafeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[{"name":"Fortemedia,Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414697"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10127"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230300"},{"key":"ref7","article-title":"FMSG submission for DCASE 2023 challenge task 4 on sound event detection with weak labels and synthetic soundscapes","volume-title":"DCASE2023 Challenge, Tech. Rep","author":"Xiao","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625974"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.02.015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32231"},{"key":"ref12","article-title":"WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System","volume-title":"Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Xiao"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616131"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414774"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414789"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0303994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10894"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095504"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies","author":"Kim"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053174"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233468"},{"key":"ref32","article-title":"FMSG-JLESS Submission for DCASE 2024 Task4 on Sound Event Detection with Heterogeneous Training Dataset and Potentially Missing Labels","volume-title":"DCASE2024 Challenge, Tech. Rep","author":"Xiao","year":"2024"},{"key":"ref33","article-title":"Mixstyle based Domain Generalization for Sound Event Detection with Heterogeneous Training Data","author":"Xiao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"ref35","article-title":"Language-queried audio source separation with GPT-based text augmentation and ideal ratio masking","volume-title":"DCASE2024 Challenge, Tech. Rep","author":"Xiao","year":"2024"},{"key":"ref36","article-title":"Language-queried audio source separation enhanced by expanded language-audio contrastive loss","volume-title":"DCASE2024 Challenge, Tech. Rep","author":"Chung","year":"2024"},{"key":"ref37","article-title":"SRPOL submission to DCASE 2024 Challenge Task 9: modeling real and imaginary components, mixit and SDR based loss","volume-title":"DCASE2024 Challenge, Tech. Rep","author":"Romaniuk","year":"2024"},{"key":"ref38","article-title":"Performance Improvement of language-queried audio source separation based on caption augmentation from large language models for DCASE Challenge 2024 TASK 9","volume-title":"DCASE2024 Challenge, Tech. Rep","author":"Lee","year":"2024"},{"key":"ref39","article-title":"DCASE 2023 Challenge TASK 4B technical report","volume-title":"DCASE2023 Challenge, Tech. Rep","author":"Chen","year":"2023"},{"key":"ref40","article-title":"Application of spectro-temporal receptive field on soft labeled sound event detection","volume-title":"DCASE2023 Challenge, Tech. Rep","author":"Min","year":"2023"},{"key":"ref41","article-title":"Sound event detection with soft labels using self-attention mechanisms for global scene feature extraction","volume-title":"DCASE2023 Challenge, Tech. Rep","author":"Tri-Do","year":"2023"},{"key":"ref42","article-title":"Sound event detection based on soft label","volume-title":"DCASE2023 Challenge, Tech. Rep","author":"Zhang","year":"2023"}],"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\/10889789.pdf?arnumber=10889789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:41Z","timestamp":1774416341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889789","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}