{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:51:07Z","timestamp":1784645467145,"version":"3.55.0"},"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"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002703","name":"Jiangsu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002703","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002703","name":"Jiangsu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002703","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889348","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["EDSep: An Effective Diffusion-Based Method for Speech Source Separation"],"prefix":"10.1109","author":[{"given":"Jinwei","family":"Dong","sequence":"first","affiliation":[{"name":"Jiangsu University,School of Computer Science and Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group, School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[{"name":"Jiangsu University,School of Computer Science and Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-700"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746882"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21372"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref14","first-page":"7164","article-title":"Voice separation with an unknown number of multiple speakers","volume-title":"International Conference on Machine Learning","author":"Nachmani"},{"key":"ref15","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096646"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.052"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3019495"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref24","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-960"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref27","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/9781108186735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref30","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095979"},{"key":"ref32","article-title":"Learning fast samplers for diffusion models by differentiating through sample quality","volume-title":"International Conference on Learning Representations","author":"Watson"},{"key":"ref33","article-title":"Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models","author":"Bao","year":"2022"},{"key":"ref34","article-title":"Gotta go fast when generating data with score-based models","author":"Jolicoeur-Martineau","year":"2021"},{"key":"ref35","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"}],"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\/10889348.pdf?arnumber=10889348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:56Z","timestamp":1774416176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889348","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}