{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:38:03Z","timestamp":1774021083671,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447818","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7425-7429","source":"Crossref","is-referenced-by-count":5,"title":["DiffRENT: A Diffusion Model for Recording Environment Transfer of Speech"],"prefix":"10.1109","author":[{"given":"Jaekwon","family":"Im","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,Republic of Korea"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Open database of spatial room impulse responses at detmold university of music","volume-title":"Audio Engineering Society Convention","volume":"149","author":"Gari","year":"2020"},{"key":"ref2","first-page":"17","article-title":"Soundspaces: Audiovisual navigation in 3d environments","volume-title":"ECCV","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115972"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521241"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471747"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"ref10","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"342","article-title":"Decoupling magnitude and phase estimation with deep resunet for music source separation","volume-title":"ISMIR","author":"Kong"},{"key":"ref12","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"ICLR","author":"Kong"},{"key":"ref13","first-page":"626","article-title":"Sdr\u2013half-baked or well done?","volume-title":"ICASSP","author":"Le Roux"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11026"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310398"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref23","article-title":"Blind arbitrary reverb matching","volume":"2","author":"Sarroff","year":"2020","journal-title":"DAFx"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00035"},{"key":"ref25","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1612524113"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447818.pdf?arnumber=10447818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:49:03Z","timestamp":1722574143000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447818","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}