{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:04:20Z","timestamp":1778537060291,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["HIDSS-0002"],"award-info":[{"award-number":["HIDSS-0002"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004785","name":"NordForsk","doi-asserted-by":"publisher","award":["86892"],"award-info":[{"award-number":["86892"]}],"id":[{"id":"10.13039\/501100004785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/msp.2024.3445871","type":"journal-article","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T19:47:33Z","timestamp":1735760853000},"page":"72-84","source":"Crossref","is-referenced-by-count":44,"title":["Diffusion Models for Audio Restoration: A review"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8704-7658","authenticated-orcid":false,"given":"Jean-Marie","family":"Lemercier","sequence":"first","affiliation":[{"name":"Universität Hamburg, Hamburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7870-4839","authenticated-orcid":false,"given":"Julius","family":"Richter","sequence":"additional","affiliation":[{"name":"Universität Hamburg, Hamburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6349-8462","authenticated-orcid":false,"given":"Simon","family":"Welker","sequence":"additional","affiliation":[{"name":"Universität Hamburg, Hamburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5719-326X","authenticated-orcid":false,"given":"Eloi","family":"Moliner","sequence":"additional","affiliation":[{"name":"Acoustics Lab of Aalto University, Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7869-292X","authenticated-orcid":false,"given":"Vesa","family":"V\u00e4lim\u00e4ki","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8678-4699","authenticated-orcid":false,"given":"Timo","family":"Gerkmann","sequence":"additional","affiliation":[{"name":"Universität Hamburg, Hamburg, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-1561-8","volume-title":"Digital Audio RestorationA Statistical Model Based Approach.","author":"Godsill","year":"1998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860.ch5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2018.2842159"},{"key":"ref4","volume-title":"Probabilistic Machine Learning: Advanced Topics.","author":"Murphy","year":"2023"},{"key":"ref5","first-page":"139","article-title":"Generative adversarial networks","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Proc. Neural Inf. Process. Syst."},{"key":"ref6","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref7","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref8","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref10","first-page":"1","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3285241"},{"key":"ref13","volume-title":"Stochastic Differential Equations: An Introduction With Applications.","author":"ksendal","year":"2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00142"},{"key":"ref15","volume-title":"Numerical Recipes: The Art of Scientific Computing","author":"Press","year":"2007"},{"key":"ref16","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3294692"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0129"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3507566"},{"key":"ref21","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref22","first-page":"1","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref23","first-page":"1","article-title":"Generative pre-training for speech with flow matching","author":"Liu","year":"2024","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref24","first-page":"1","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1445"},{"key":"ref26","first-page":"1","article-title":"Denoising diffusion gamma models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nachmani","year":"2022"},{"key":"ref27","first-page":"1","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chung","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248108"},{"key":"ref29","first-page":"659","article-title":"A study on speech enhancement based on diffusion probabilistic model","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. (APSIPA)","author":"Lu","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095396"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC61483.2024.10694254"},{"key":"ref33","first-page":"1","article-title":"Empirical distributions of DFT-domain speech coefficients based on estimated speech variances","volume-title":"Proc. Int. Workshop Acoust. Signal Enhancement","author":"Gerkmann","year":"2010"},{"key":"ref34","first-page":"71340","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref35","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref37","first-page":"1","article-title":"BDDM: Bilateral denoising diffusion models for fast and high-quality speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lam","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447860"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ojsp.2024.3379070"},{"key":"ref40","first-page":"275","article-title":"Audio-visual speech enhancement with score-based generative models","volume-title":"Proc. ITG Conf. Speech Commun.","author":"Richter","year":"2023"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/79\/10819667\/10819705.pdf?arnumber=10819705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T09:44:55Z","timestamp":1736588695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10819705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/msp.2024.3445871","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}