{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T14:56:11Z","timestamp":1777733771848,"version":"3.51.4"},"reference-count":33,"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\/icassp49660.2025.10890066","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":9,"title":["SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Helin","family":"Wang","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"}]},{"given":"Jiarui","family":"Hai","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"}]},{"given":"Yen-Ju","family":"Lu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"}]},{"given":"Karan","family":"Thakkar","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"}]},{"given":"Mounya","family":"Elhilali","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-676"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1369"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447525"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2210"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095266"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"gddim: Generalized denoising diffusion implicit models","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-327"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447219"},{"key":"ref15","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Mariani"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1234"},{"key":"ref17","article-title":"Separate anything you describe","volume":"abs\/2308.05037","author":"Liu","year":"2023","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SynData4GenAI.2024-1"},{"key":"ref20","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017, Suzhou, China, October 23-27, 2017","author":"Fonseca"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref22","article-title":"Ezaudio: Enhancing text-to-audio generation with efficient diffusion transformer","volume":"abs\/2409.10819","author":"Hai","year":"2024","journal-title":"CoRR"},{"key":"ref23","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","author":"Evans"},{"key":"ref24","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref28","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","volume-title":"Scenes and Events 2018 Workshop (DCASE2018)","author":"Mesaros"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref32","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","volume":"202","author":"Liu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"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\/10890066.pdf?arnumber=10890066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:58Z","timestamp":1774416238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890066","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}