{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:18:48Z","timestamp":1780496328321,"version":"3.54.1"},"reference-count":35,"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\/icassp49357.2023.10095637","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":43,"title":["Solving Audio Inverse Problems with a Diffusion Model"],"prefix":"10.1109","author":[{"given":"Eloi","family":"Moliner","sequence":"first","affiliation":[{"name":"Aalto University,Acoustics Lab,Dept. of Information & Communications Eng.,Espoo,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaakko","family":"Lehtinen","sequence":"additional","affiliation":[{"name":"Aalto University,Dept. of Computer Science,Espoo,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vesa","family":"V\u00e4lim\u00e4ki","sequence":"additional","affiliation":[{"name":"Aalto University,Acoustics Lab,Dept. of Information & Communications Eng.,Espoo,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Multi-instrument music synthesis with spectrogram diffusion","author":"hawthorne","year":"2022","journal-title":"Proc ISMIR"},{"key":"ref35","first-page":"2350","article-title":"Fréchet audio distance: A reference-free metric for evaluating music enhancement algorithms","author":"kilgour","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref12","article-title":"CRASH: Raw audio score-based generative modeling for controllable high-resolution drum sound synthesis","author":"rouard","year":"2021","journal-title":"Proc ISMIR"},{"key":"ref34","first-page":"20916","article-title":"Catch-a-waveform: Learning to generate audio from a single short example","volume":"34","author":"greshler","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref15","article-title":"Improving diffusion models for inverse problems using manifold constraints","author":"chung","year":"2022","journal-title":"Proc NeurIPS"},{"key":"ref14","article-title":"Denoising diffusion restoration models","author":"kawar","year":"2022","journal-title":"Proc ICLR"},{"key":"ref31","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"2019","journal-title":"Proc ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref11","article-title":"Universal speech enhancement with score-based diffusion","author":"serr\u00e0","year":"2022"},{"key":"ref33","article-title":"Sequence-to-sequence piano transcription with transformers","author":"hawthorne","year":"2021","journal-title":"Proc IS-MIR"},{"key":"ref10","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"Proc ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3037485"},{"key":"ref2","first-page":"1577","article-title":"Audio declip-ping with social sparsity","author":"siedenburg","year":"2014","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_28"},{"key":"ref17","first-page":"7616","article-title":"It’s raw! Audio generation with state-space models","author":"goel","year":"2022","journal-title":"Proc 39th Int Conf Machine Learning"},{"key":"ref16","article-title":"Diffusion posterior sampling for general noisy inverse problems","author":"chung","year":"2023","journal-title":"Proc ICLR"},{"key":"ref19","article-title":"Speech enhancement and dereverberation with diffusion-based generative models","author":"richter","year":"2022"},{"key":"ref18","first-page":"240","article-title":"Realistic gramophone noise synthesis using a diffusion model","author":"moliner","year":"2022","journal-title":"Proc Int Conf Digital Audio Effects (DAFx)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref26","article-title":"Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"kim","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053669"},{"key":"ref22","article-title":"Elucidating the design space of diffusion-based generative models","author":"karras","year":"2022","journal-title":"Proc NeurIPS"},{"key":"ref21","article-title":"TimbreTron: A WaveNet(CycleGAN(CQT(audio))) pipeline for musical timbre transfer","author":"huang","year":"2019","journal-title":"Proc ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref27","article-title":"Constructing an invertible constant-Q transform with non-stationary Gabor frames","author":"velasco","year":"2011","journal-title":"Proc Int Conf Digital Audio Effects (DAFx)"},{"key":"ref29","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"tancik","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2021","journal-title":"Proc ICLR"},{"key":"ref9","article-title":"Video diffusion models","author":"ho","year":"2022","journal-title":"Proc NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190726"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2869113"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3037506"}],"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\/10095637.pdf?arnumber=10095637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:06Z","timestamp":1700507106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095637","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}