{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:52Z","timestamp":1764403252645,"version":"3.28.0"},"reference-count":24,"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\/icassp49357.2023.10095769","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":4,"title":["MAID: A Conditional Diffusion Model for Long Music Audio Inpainting"],"prefix":"10.1109","author":[{"given":"Kaiyang","family":"Liu","sequence":"first","affiliation":[{"name":"Sichuan University,College of Computer Science,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wendong","family":"Gan","sequence":"additional","affiliation":[{"name":"Wiz Holdings Pte Ltd,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenchen","family":"Yuan","sequence":"additional","affiliation":[{"name":"Sichuan University,College of Computer Science,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref13","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00037"},{"key":"ref23","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref15","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2021","journal-title":"ICLRE"},{"key":"ref14","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"JMLR"},{"key":"ref20","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"2019","journal-title":"ICLRE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-194"},{"key":"ref22","article-title":"Intuitive analysis, creation and manipulation of midi data with pretty_midi","author":"raffel","year":"2014","journal-title":"ISMIR Late Breaking and Demo Papers"},{"article-title":"Armas: Active re-construction of missing audio segments","year":"2021","author":"cheddad","key":"ref10"},{"key":"ref21","article-title":"Learning features of music from scratch","author":"thickstun","year":"2017","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902560"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2168211"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"ramesh","key":"ref17"},{"key":"ref16","article-title":"Diffusion models beat GANs on image synthesis","author":"dhariwal","year":"2021","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1109\/TASLP.2017.2678166","article-title":"A noniterative method for reconstruction of phase from stft magnitude","volume":"25","author":"pra","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref18","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"ICLRE"},{"article-title":"Audio inpainting with generative adversarial network","year":"2020","author":"ebner","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2809864"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3037506"},{"article-title":"Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization","year":"2022","author":"mokr\u00fd","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030486"},{"article-title":"Deep long audio inpainting","year":"2019","author":"chang","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2947232"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095769.pdf?arnumber=10095769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:20Z","timestamp":1700506940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095769","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}