{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:55:19Z","timestamp":1776887719956,"version":"3.51.2"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446423","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"596-600","source":"Crossref","is-referenced-by-count":5,"title":["VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance"],"prefix":"10.1109","author":[{"given":"Carlos","family":"Hernandez-Olivan","sequence":"first","affiliation":[{"name":"University of Zaragoza,Dept. of Electronic Engineering and Communications,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Saito","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Murata","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chieh-Hsin","family":"Lai","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco A.","family":"Mart\u00ednez-Ram\u00edrez","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Hsiang","family":"Liao","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1890"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3042071"},{"key":"ref3","article-title":"Distortion Audio Effects: Learning How to Recover the Clean Signal","volume-title":"Proc. ISMIR","author":"Imort"},{"key":"ref4","article-title":"Audio super resolution using neural networks","volume":"abs\/1708.00853","author":"Kuleshov","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190726"},{"key":"ref6","article-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI","volume":"abs\/2303.13336","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095761"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10735"},{"key":"ref10","article-title":"GibbsDDRM: A partially collapsed gibbs sampler for solving blind inverse problems with denoising diffusion restoration","volume-title":"ICML","author":"Murata"},{"key":"ref11","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume":"abs\/2209.14687","author":"Chung","year":"2022","journal-title":"CoRR"},{"key":"ref12","first-page":"8633","article-title":"Video diffusion models","volume-title":"Advances in Neural Inf. Proc. Systems","volume":"35","author":"Ho"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref14","article-title":"Pseudoinverse-guided diffusion models for inverse problems","volume-title":"ICLR","author":"Song"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref16","article-title":"Combining pitch-based inference and non-negative spectrogram factorization in separating vocals from polyphonic music","volume-title":"Proc. Interspeech","author":"Virtanen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref19","article-title":"Denoising diffusion restoration models","volume-title":"NeurIPS","author":"Kawar"},{"key":"ref20","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref21","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref22","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"NeurIPS","author":"Karras"},{"issue":"24","key":"ref23","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref27","author":"Rafii","year":"2017","journal-title":"The MUSDB18 corpus for music separation"},{"key":"ref28","article-title":"Constructing an invertible constant-q transform with nonstationary gabor frames","volume-title":"Proc. DAFx","author":"Velasco"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref31","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","author":"Telecommunication Union","year":"2015","journal-title":"ITU-R Recommendation ITU-R BS.1534-3"}],"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\/10446423.pdf?arnumber=10446423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:08Z","timestamp":1722573428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446423","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}