{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:15:51Z","timestamp":1776888951729,"version":"3.51.2"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889421","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models"],"prefix":"10.1109","author":[{"given":"Tornike","family":"Karchkhadze","sequence":"first","affiliation":[{"name":"University of California San Diego,San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Rasool","family":"Izadi","sequence":"additional","affiliation":[{"name":"Bose Corp.,Framingham,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shlomo","family":"Dubnov","sequence":"additional","affiliation":[{"name":"University of California San Diego,San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413896"},{"key":"ref2","article-title":"Hybrid spectrogram and waveform source separation","author":"D\u00e9fossez","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1177"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746530"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref6","article-title":"Music source separation in the waveform domain","author":"D\u00e9fossez","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461671"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/381"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3115"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3219355"},{"key":"ref12","first-page":"4807","article-title":"Parallel and flexible sampling from autoregressive models via langevin dynamics","volume-title":"Proc. ICML","author":"Jayaram"},{"key":"ref13","first-page":"4724","article-title":"Source separation with deep generative priors","volume-title":"Proc. ICML","author":"Jayaram"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747076"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096847"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref17","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"NeurIPS","volume":"33","author":"Wisdom"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","volume":"33","author":"Ho"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref20","article-title":"Separate and diffuse: Using a pretrained diffusion model for improving source separation","author":"Lutati","year":"2023"},{"key":"ref21","article-title":"Davis: High-quality audio-visual separation with generative diffusion models","author":"Huang","year":"2023"},{"key":"ref22","first-page":"553","article-title":"Carnatic singing voice separation using cold diffusion on training data with bleeding","volume-title":"Proc. ISMIR","author":"Plaja-Roglans"},{"key":"ref23","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"ICLR","author":"Mariani"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref25","article-title":"Samplernn: An unconditional end-to-end neural audio generation model","volume-title":"ICLR","author":"Mehri"},{"key":"ref26","article-title":"Adversarial audio synthesis","volume-title":"ICLR","author":"Donahue"},{"key":"ref27","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref28","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref29","article-title":"Simple and controllable music generation","volume-title":"NeurIPS","author":"Copet"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.437"},{"key":"ref33","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"ICLR","author":"Kong"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33584"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446400"},{"key":"ref37","article-title":"Singsong: Generating musical accompaniments from singing","author":"Donahue","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97257-7_6"},{"key":"ref39","article-title":"Diff-a-riff: Musical accompaniment co-creation via latent diffusion models","author":"Nistal","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3244620"},{"key":"ref41","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"ICML","volume":"202","author":"Liu"},{"key":"ref42","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref46","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NeurIPS","volume":"33","author":"Kong"},{"key":"ref47","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","volume":"37","author":"Sohl-Dickstein"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref51","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song"},{"key":"ref52","first-page":"626","article-title":"Sdr \u2013 half-baked or well done?","volume-title":"ICASSP","author":"Roux"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889421.pdf?arnumber=10889421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:18Z","timestamp":1774416318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889421","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}