{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T20:01:54Z","timestamp":1785700914377,"version":"3.56.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746901","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7402-7406","source":"Crossref","is-referenced-by-count":191,"title":["Conditional Diffusion Probabilistic Model for Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Yen-Ju","family":"Lu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Richard","sequence":"additional","affiliation":[{"name":"Reality Labs Research,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3040693"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2528\/PIERM08061206"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref36","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020"},{"key":"ref35","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref10","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"2019","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946789"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462622"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-224"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.5112828"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref2","article-title":"Far-field automatic speech recognition","author":"haeb-umbach","year":"2020","journal-title":"Proceedings of the IEEE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842156"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref20","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"Proc ICML"},{"key":"ref22","article-title":"Improved denoising diffusion probabilistic models","author":"nichol","year":"2021"},{"key":"ref21","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref23","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2020"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"146","DOI":"10.21437\/SSW.2016-24","article-title":"Investigating RNN-based speech enhancement methods for noise-robust text-to-speech","author":"valentini-botinhao","year":"2016","journal-title":"SSW"},{"key":"ref25","article-title":"A study on speech enhancement based on diffusion probabilistic model","author":"lu","year":"2021"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746901.pdf?arnumber=9746901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:36Z","timestamp":1661199096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746901","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}