{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:05:06Z","timestamp":1773273906435,"version":"3.50.1"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11231013","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":["Hybrid-Sep: Language-queried audio source separation via pre-trained Model Fusion and Adversarial Consistent Training"],"prefix":"10.1109","author":[{"given":"Jianyuan","family":"Feng","sequence":"first","affiliation":[{"name":"ByteDance,China"}]},{"given":"Guangzheng","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance,China"}]},{"given":"Yangfei","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3520017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889789"},{"key":"ref3","article-title":"Performance improvement of language-queried audio source separation based on caption augmentation from large language models for dcase challenge 2024 task 9","author":"Lee","year":"2024"},{"key":"ref4","article-title":"Language-queried audio source separation enhanced by expanded language-audio contrastive loss","volume-title":"Tech. Rep, Tech. Rep.","author":"Chung","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890129"},{"key":"ref6","article-title":"A reference-free metric for language-queried audio source separation using contrastive language-audio pretraining","author":"Xiao","year":"2024"},{"key":"ref7","article-title":"Fr\\\u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018"},{"key":"ref8","article-title":"Consistency models","author":"Song","year":"2023"},{"key":"ref9","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734763"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022"},{"key":"ref15","article-title":"Mert: Acoustic music under-standing model with large-scale self-supervised training","author":"Li","year":"2023"},{"key":"ref16","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref17","article-title":"Improved techniques for training consistency models","author":"Song","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172176"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","article-title":"The musdb18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ojsp.2024.3378602"},{"key":"ref23","article-title":"Audiocaps: Generating captions for audios in the wild","author":"Kim","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref25","article-title":"Clotho: An audio captioning dataset","author":"Drossos","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"}],"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\/11231013.pdf?arnumber=11231013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:38:38Z","timestamp":1763404718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11231013","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}