{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:22:11Z","timestamp":1776885731087,"version":"3.51.2"},"reference-count":46,"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\/waspaa66052.2025.11230963","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":1,"title":["Source Separation by Flow Matching"],"prefix":"10.1109","author":[{"given":"Robin","family":"Scheibler","sequence":"first","affiliation":[{"name":"Google DeepMind"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Arnaud","family":"Doucet","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Henry","family":"Li","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73031-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2297715"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1433"},{"key":"ref7","article-title":"Mel-band RoFormer for music source separation","volume-title":"ISMIR","author":"Wang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC61483.2024.10694313"},{"key":"ref9","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"ICML","author":"Larsen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461671"},{"key":"ref11","first-page":"4724","article-title":"Source separation with deep generative priors","volume-title":"ICML","author":"Jayaram"},{"key":"ref12","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song"},{"key":"ref15","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"Chen","year":"2021","journal-title":"ICLR"},{"key":"ref16","article-title":"PriorGrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","volume-title":"ICLR","author":"Lee"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2024.3445871"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095979"},{"key":"ref21","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"ICLR","author":"Mariani"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-327"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889348"},{"key":"ref25","article-title":"Non-denoising forward-time diffusions","author":"Peluchetti","year":"2021"},{"key":"ref26","article-title":"Diffusion Schr\u00f6dinger bridge with applications to score-based generative modeling","author":"De Bortoli","year":"2021","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Flow matching for generative modeling","volume-title":"ICLR","author":"Lipman"},{"key":"ref28","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","author":"Albergo","year":"2023"},{"key":"ref29","article-title":"Let us build bridges: Understanding and extending diffusion generative models","author":"Liu","year":"2022"},{"key":"ref30","article-title":"Zero-shot image restoration using denoising diffusion null-space model","volume-title":"ICLR","author":"Wang"},{"key":"ref31","article-title":"Equivariant flow matching","volume":"36","author":"Klein","year":"2024","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"ICLR","author":"Chung"},{"key":"ref33","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2024","journal-title":"Transact. mach. learn. res."},{"key":"ref34","article-title":"Conditional Wasserstein distances with applications in Bayesian OT flow matching","author":"Chemseddine","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2968"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref37","article-title":"Neural diffusion processes","volume-title":"ICML","author":"Dutordoir"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref39","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref44","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)","author":"Rix","year":"2001","journal-title":"ICASSP"},{"issue":"6","key":"ref45","article-title":"Perceptual objective listening quality assessment (POLQA), the third generation ITU-T standard for end-to-end speech quality measurement part I\u2013Temporal alignment","volume":"61","author":"Beerends","year":"2013","journal-title":"J. Audio Eng. Soc."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"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\/11230963.pdf?arnumber=11230963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:42Z","timestamp":1763191962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230963\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230963","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}