{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T13:40:15Z","timestamp":1778852415102,"version":"3.51.4"},"reference-count":74,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Nordic Sound and Music Computing Network—NordicSMC, NordForsk","award":["86892"],"award-info":[{"award-number":["86892"]}]}],"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.2024.3507566","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:44:02Z","timestamp":1732736642000},"page":"5092-5105","source":"Crossref","is-referenced-by-count":10,"title":["Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5719-326X","authenticated-orcid":false,"given":"Eloi","family":"Moliner","sequence":"first","affiliation":[{"name":"Acoustics Laboratory, Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1857-2173","authenticated-orcid":false,"given":"Filip","family":"Elvander","sequence":"additional","affiliation":[{"name":"Acoustics Laboratory, Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7869-292X","authenticated-orcid":false,"given":"Vesa","family":"V\u00e4lim\u00e4ki","sequence":"additional","affiliation":[{"name":"Acoustics Laboratory, Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Efficient high-frequency bandwidth extension of music and speech","author":"Larsen","year":"2002"},{"key":"ref2","first-page":"173","article-title":"High frequency magnitude spectrogram reconstruction for music mixtures using convolutional autoencoders","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Miron","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054194"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190726"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-892"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937169"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3037485"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11026"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095258"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170672"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472812"},{"key":"ref16","first-page":"1178","article-title":"Bandwidth enhancement of narrow-band speech signals","volume-title":"Proc. Eur. Signal Process. Conf.","volume":"2","author":"Carl","year":"1994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/0470858710"},{"key":"ref18","article-title":"Spectral band replication, a novel approach in audio coding","volume-title":"Proc. Audio Eng. Soc. 112th Conv.","author":"Dietz","year":"2002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854773"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198872"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118206"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178801"},{"key":"ref25","article-title":"Audio super resolution using neural nets","volume-title":"Proc. Int. Conf. Learn. Represent. (Workshop Track)","author":"Kuleshov","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054302"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909077"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413575"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413439"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095103"},{"key":"ref32","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.437"},{"key":"ref34","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096064"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref38","article-title":"Denoising diffusion probabilistic models for robust image super-resolution in the wild","author":"Sahak","year":"2023"},{"key":"ref39","article-title":"DriftRec: Adapting diffusion models to blind image restoration tasks","volume-title":"Proc. NeurIPS 2022 Workshop DLDE","author":"Welker","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00587"},{"key":"ref41","article-title":"GibbsDDRM: A partially collapsed Gibbs sampler for solving blind inverse problems with denoising diffusion restoration","volume-title":"Proc. ICML","author":"Murata","year":"2023"},{"key":"ref42","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chung","year":"2023"},{"key":"ref43","article-title":"Denoising diffusion restoration models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kawar","year":"2022"},{"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","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Karras","year":"2022"},{"issue":"4","key":"ref46","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyvrinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","first-page":"899","article-title":"Generalized denoising auto-encoders as generative models","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Bengio","year":"2013"},{"key":"ref48","article-title":"Understanding diffusion objectives as the ELBO with simple data augmentation","volume-title":"Proc. NeuRIPS","author":"Kingma","year":"2023"},{"key":"ref49","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref50","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Song","year":"2019"},{"key":"ref51","article-title":"A variational perspective on solving inverse problems with diffusion models","volume-title":"Proc. ICLR","author":"Mardani","year":"2024"},{"key":"ref52","article-title":"Generative modelling with inverse heat dissipation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rissanen","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"ref56","volume-title":"Manual of Analogue Sound Restoration Techniques","author":"Copeland","year":"2008"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746977"},{"key":"ref59","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2022"},{"key":"ref60","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":"ref61","first-page":"93","article-title":"Constructing an invertible constant-Q transform with non-stationary Gabor frames","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Velasco","year":"2011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0129"},{"key":"ref63","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hawthorne","year":"2019"},{"key":"ref64","article-title":"The chamber ensemble generator: Limitless high-quality MIR data via generative modeling","author":"Wu","year":"2022"},{"key":"ref65","article-title":"MIDI-DDSP: Detailed control of musical performance via hierarchical modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2022"},{"key":"ref66","first-page":"2350","article-title":"Frchet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume-title":"Proc. Interspeech","author":"Kilgour","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref68","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref70","article-title":"Method for the Subjective Assessment of Intermediate Quality Level of Audio Systems","year":"2015"},{"key":"ref71","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":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30441-0_40"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0009"},{"key":"ref74","first-page":"25","article-title":"A diffusion-based generative equalizer for music restoration","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Moliner","year":"2024"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10768977.pdf?arnumber=10768977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T22:10:48Z","timestamp":1733955048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10768977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3507566","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}