{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T06:36:58Z","timestamp":1783665418625,"version":"3.55.0"},"reference-count":104,"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-nc-nd\/4.0\/"}],"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.2024.3473319","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:24:40Z","timestamp":1727976280000},"page":"4486-4500","source":"Crossref","is-referenced-by-count":24,"title":["Investigating the Design Space of Diffusion Models for Speech Enhancement"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4965-3514","authenticated-orcid":false,"given":"Philippe","family":"Gonzalez","sequence":"first","affiliation":[{"name":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-8928","authenticated-orcid":false,"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3724-6114","authenticated-orcid":false,"given":"Jan","family":"\u00d8stergaard","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1478-622X","authenticated-orcid":false,"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0941-3146","authenticated-orcid":false,"given":"Tommy Sonne","family":"Alstr\u00f8m","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5463-5509","authenticated-orcid":false,"given":"Tobias","family":"May","sequence":"additional","affiliation":[{"name":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1704.724"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2403.375"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.02.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.03.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2158309"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2193391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196924"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946789"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref13","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref14","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"37","author":"Rezende","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2979603"},{"key":"ref18","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"37","author":"Sohl-Dickstein","year":"2015"},{"key":"ref19","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096064"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095046"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096985"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1547"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095850"},{"key":"ref31","first-page":"40272","article-title":"DOSE: Diffusion dropout with adaptive prior for speech enhancement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tai","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448429"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446610"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447736"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446805"},{"key":"ref36","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref39","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Popov","year":"2021"},{"key":"ref40","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Liu","year":"2023"},{"key":"ref41","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2022"},{"key":"ref42","article-title":"Imagen Video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref43","first-page":"23593","article-title":"Denoising diffusion restoration models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kawar","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01581"},{"key":"ref45","first-page":"25683","article-title":"Improving diffusion models for inverse problems using manifold constraints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chung","year":"2022"},{"key":"ref46","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chung","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248108"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-367"},{"key":"ref50","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karras","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095258"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1445"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"issue":"24","key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref56","first-page":"574","article-title":"Sliced score matching: A scalable approach to density and score estimation","volume-title":"Proc. Uncertainty Artif. Intell.","volume":"115","author":"Song","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/9781108186735"},{"key":"ref58","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2021"},{"key":"ref59","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2022"},{"key":"ref60","first-page":"13213","article-title":"Simple diffusion: End-to-end diffusion for high resolution images","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Hoogeboom","year":"2023"},{"key":"ref61","first-page":"65484","article-title":"Understanding diffusion objectives as the ELBO with simple data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2023"},{"key":"ref62","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Nichol","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1265"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3318965"},{"key":"ref69","article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM, NIST speech disc 1-1.1","author":"Garofolo","year":"1993"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.107951"},{"key":"ref73","article-title":"TAU urban acoustic scenes 2019, development dataset","author":"Heittola","year":"2019","journal-title":"Zenodo"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3109\/00206090109073110"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3813\/AAA.919349"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051354"},{"key":"ref78","article-title":"Audio spatialisation for headphonesimpulse response dataset","author":"Pearce","year":"2021","journal-title":"Zenodo"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107867"},{"key":"ref80","article-title":"Simulated room impulse responses"},{"key":"ref81","article-title":"Database of simulated impulse responses and a scene constructor framework for the audiovisual immersion lab (AVIL) at DTU","author":"Marschall","year":"2017","journal-title":"Zenodo"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1121\/1.4789895"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1121\/1.1506692"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref85","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097075"},{"key":"ref87","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747120"},{"key":"ref91","article-title":"Exploring the best loss function for DNN-based low-latency speech enhancement with temporal convolutional networks","author":"Koyama","year":"2020"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref93","first-page":"626","article-title":"SDRhalf-baked or well done?","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Roux","year":"2019"},{"key":"ref94","article-title":"Deep complex networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Trabelsi","year":"2018"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-686"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref103","article-title":"Perceptual Evaluation of Speech Quality (PESQ): An Objective Method for End-to-End Speech Quality Assessment of Narrow-Band Telephone Networks and Speech Codecs","volume":"862","year":"2001"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10704960.pdf?arnumber=10704960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:39:12Z","timestamp":1732667952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10704960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":104,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3473319","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}