{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:03:33Z","timestamp":1778299413566,"version":"3.51.4"},"reference-count":37,"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\/icassp49660.2025.10888769","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging Audio-Only Data for Text-Queried Target Sound Extraction"],"prefix":"10.1109","author":[{"given":"Kohei","family":"Saijo","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janek","family":"Ebbers","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois G.","family":"Germain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sameer","family":"Khurana","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gordon","family":"Wiehern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC61483.2024.10694313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10894"},{"key":"ref13","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":"ref14","article-title":"CLIPSep: Learning text-queried sound separation with noisy unlabeled videos","volume-title":"Proc. ICLR","author":"Dong"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref17","first-page":"17 612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Liang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"key":"ref20","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL","author":"Kim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref22","first-page":"21 450","article-title":"AudioLDM: text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448115"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref28","article-title":"Separate anything you describe","author":"Liu","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1389"},{"key":"ref34","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref36","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"}],"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\/10888769.pdf?arnumber=10888769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:05Z","timestamp":1774416185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888769","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}