{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T07:46:21Z","timestamp":1780472781805,"version":"3.54.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447219","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1196-1200","source":"Crossref","is-referenced-by-count":10,"title":["DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction"],"prefix":"10.1109","author":[{"given":"Jiarui","family":"Hai","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helin","family":"Wang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongchao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karan","family":"Thakkar","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mounya","family":"Elhilali","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082331"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1369"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053396"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2210"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-676"},{"key":"ref9","article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref11","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1234"},{"key":"ref16","article-title":"Conditional diffusion model for target speaker extraction","author":"Nguyen","year":"2023"},{"key":"ref17","first-page":"486","article-title":"Freesound datasets: a platform for the creation of open audio datasets","author":"Fonseca","year":"2017","journal-title":"International Society for Music Information Retrieval (ISMIR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref21","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref23","first-page":"9","article-title":"A multidevice dataset for urban acoustic scene classification","volume-title":"Scenes and Events 2018 Workshop (DCASE2018)","author":"Mesaros"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1219"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462153"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447219.pdf?arnumber=10447219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:32:33Z","timestamp":1722576753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447219","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}