{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:37:43Z","timestamp":1763192263012,"version":"3.45.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11231006","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior"],"prefix":"10.1109","author":[{"given":"Chin-Yun","family":"Yu","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,London,UK"}]},{"given":"Marco A.","family":"Mart\u00ednez-Ram\u00edrez","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Junghyun","family":"Koo","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Wei-Hsiang","family":"Liao","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Gy\u00f6rgy","family":"Fazekas","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,London,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0123"},{"article-title":"Automatic music mixing with deep learning and out-of-domain data","volume-title":"Proc. ISMIR","author":"Martinez Ramirez","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096458"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414364"},{"key":"ref6","first-page":"563","article-title":"Diff-MST: Differentiable mixing style transfer","volume-title":"Proc. ISMIR","author":"Vanka"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890334"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref9","first-page":"661","article-title":"ST-ITO: Controlling audio effects for style transfer with inference-time optimization","author":"Steinmetz","year":"2024","journal-title":"ISMIR"},{"article-title":"ITO-Master: Inference-time optimization for music mastering style transfer","volume-title":"Proc. ISMIR","author":"Koo","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747909"},{"key":"ref12","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. ICML","author":"Sohl-Dickstein"},{"article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song","key":"ref13"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. ICLR","author":"Chung","key":"ref15"},{"key":"ref16","first-page":"23 593","article-title":"Denoising diffusion restoration models","volume-title":"Proc. NeurIPS","volume":"35","author":"Kawar"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446423"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2024.3445871"},{"article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"Proc. ICLR","author":"Mariani","key":"ref20"},{"article-title":"Diffusion-based Signal Refiner for Speech Separation","year":"2023","author":"Hirano","key":"ref21"},{"article-title":"DITTO: Diffusion inference-time t-optimization for music generation","volume-title":"Proc. ICML","author":"Novack","key":"ref22"},{"key":"ref23","first-page":"874","article-title":"DITTO-2: Distilled diffusion inference-time t-optimization for music generation","volume-title":"Proc. ISMIR","author":"Novack"},{"article-title":"DiffVox: A differentiable model for capturing and analysing vocal effects distributions","volume-title":"Proc. DAFx","author":"Yu","key":"ref24"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref27","first-page":"248","article-title":"A direct microdynamics adjusting processor with matching paradigm and differentiable implementation","volume-title":"Proc. DAFx","author":"Nercessian"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034828"},{"key":"ref29","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive mir research","volume-title":"Proc. ISMIR","author":"Bittner"},{"key":"ref30","article-title":"MedleyDB 2.0: New data and a system for sustainable data collection","author":"Bittner","year":"2016","journal-title":"ISMIR Late Breaking and Demo Papers"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref32","first-page":"137","article-title":"An analysis and evaluation of audio features for multitrack music mixtures","volume-title":"Proc. ISMIR","author":"Man"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2015.0053"},{"article-title":"A variational perspective on solving inverse problems with diffusion models","volume-title":"Proc. ICLR","author":"Mardani","key":"ref34"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448301"},{"article-title":"Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching","volume-title":"Proc. ISMIR","author":"Hayes","key":"ref37"},{"key":"ref38","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","volume":"2","author":"Series","year":"2014","journal-title":"International Telecommunication Union Radiocommunication Assembly"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393738"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096581"},{"key":"ref43","article-title":"The responsibility problem in neural networks with unordered targets","volume-title":"Tiny Papers@ICLR","author":"Hayes","year":"2023"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11231006.pdf?arnumber=11231006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:00Z","timestamp":1763191980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11231006","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}