{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T08:17:39Z","timestamp":1782980259368,"version":"3.54.5"},"reference-count":32,"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\/icassp43922.2022.9747454","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3124-3128","source":"Crossref","is-referenced-by-count":9,"title":["Music Enhancement via Image Translation and Vocoding"],"prefix":"10.1109","author":[{"given":"Nikhil","family":"Kandpal","sequence":"first","affiliation":[{"name":"University of North Carolina at Chapel Hill,Computer Science Department,Chapel Hill,NC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oriol","family":"Nieto","sequence":"additional","affiliation":[{"name":"Adobe Research,San Francisco,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Adobe Research,San Francisco,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Fréchet audio distance: A metric for evaluating music enhancement algorithms","author":"kilgour","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref10","first-page":"982","article-title":"Learning spectral mapping for speech dereverberation and denoising","volume":"23","author":"han","year":"2015","journal-title":"IEEE\/ACM TASLP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953226"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1620","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2688"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref15","first-page":"7143","author":"polyak","year":"2021","journal-title":"ICASSP 2021-2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref17","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-41"},{"key":"ref19","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"chen","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021"},{"key":"ref27","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2017"},{"key":"ref3","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"ref29","article-title":"Torchaudio: Building blocks for audio and speech processing","author":"yang","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413575"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref9","first-page":"31","article-title":"Joint separation and dereverberation of reverberant mixtures with determined multichannel non-negative matrix factorization","author":"kagami","year":"2018","journal-title":"IEEE ICASSP 2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref21","article-title":"Music source separation in the waveform domain","author":"d\u00e9fossez","year":"2021"},{"key":"ref24","article-title":"Deep convolutional networks on the pitch spiral for musical instrument recognition","author":"lostanlen","year":"2017"},{"key":"ref23","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336912"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"}],"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\/09747454.pdf?arnumber=9747454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:09:33Z","timestamp":1660594173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747454","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}