{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T03:02:32Z","timestamp":1784430152534,"version":"3.55.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171427"],"award-info":[{"award-number":["62171427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3407533","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T21:08:18Z","timestamp":1717535298000},"page":"3025-3038","source":"Crossref","is-referenced-by-count":15,"title":["A Variance-Preserving Interpolation Approach for Diffusion Models With Applications to Single Channel Speech Enhancement and Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0486-6088","authenticated-orcid":false,"given":"Zilu","family":"Guo","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-3920","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing-Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"ref2","volume-title":"Automatic Speech Recognition","author":"Yu","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.91"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-120"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3119927"},{"key":"ref12","first-page":"19935","article-title":"Unsupervised noise adaptive speech enhancement by discriminator-constrained optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1979.11540"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2996503"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858066"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-224"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3207349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413999"},{"key":"ref25","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref28","first-page":"659","article-title":"A study on speech enhancement based on diffusion probabilistic model","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Lu","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1889"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1265"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095850"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096064"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095761"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095046"},{"key":"ref39","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref43","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Popov","year":"2021"},{"key":"ref44","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/9781108186735"},{"key":"ref46","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kingma","year":"2021"},{"issue":"15","key":"ref47","article-title":"The matrix cookbook","volume-title":"Tech. Univ. Denmark","volume":"7","author":"Petersen","year":"2008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1025-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746609"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10547426.pdf?arnumber=10547426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:00:52Z","timestamp":1750100452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10547426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3407533","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}