{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:02:12Z","timestamp":1780675332993,"version":"3.54.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096064","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":39,"title":["Cold Diffusion for Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Hao","family":"Yen","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois G.","family":"Germain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref35","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"valentini-botinhao","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref15","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"2019","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref33","article-title":"Deep complex networks","author":"trabelsi","year":"2018","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref2","article-title":"Phasesensitive and recognition-boosted speech separation using deep recurrent neural networks","author":"erdogan","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414060"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747029"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632676"},{"key":"ref38","article-title":"Improved denoising apion probabilistic models","author":"nichol","year":"2021","journal-title":"Proc ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3207349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref23","article-title":"A study on speech enhancement based on apsipsion probabilistic model","author":"lu","year":"2021","journal-title":"Proc APSIPA ASC"},{"key":"ref26","article-title":"Universal speech enhancement with score-based apsipaion","author":"serr\u00e0","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref20","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"Proc ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref22","article-title":"Denoising apion implicit models","author":"song","year":"2021","journal-title":"Proc ICLR"},{"key":"ref21","article-title":"Denoising apsipaion probabilistic models","author":"ho","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref28","article-title":"DiffWave: A versatile apion model for audio synthesis","author":"kong","year":"2021","journal-title":"Proc ICLR"},{"key":"ref27","article-title":"Cold apion: Inverting arbitrary image transforms without noise","author":"bansal","year":"2022"},{"key":"ref29","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc SSW"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.5112828"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref4","article-title":"Speech enhancement with a generative adversarial network","author":"vik","year":"2019","journal-title":"Master’s thesis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2017.7864754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2986896"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3040693"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096064.pdf?arnumber=10096064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:21Z","timestamp":1699902201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096064","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}