{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:23:06Z","timestamp":1776885786853,"version":"3.51.2"},"reference-count":35,"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\/icassp49660.2025.10890052","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":2,"title":["MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling"],"prefix":"10.1109","author":[{"given":"Simon","family":"Rouard","sequence":"first","affiliation":[{"name":"Meta & UMR STMS IRCAM-CNRS-Sorbonne Univ"}]},{"given":"Robin San","family":"Roman","sequence":"additional","affiliation":[{"name":"Meta, FAIR, Univ. de Lorraine, CNRS, Inria, Loria"}]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[{"name":"Meta & Hebrew Univ. of Jerusalem"}]},{"given":"Axel","family":"Roebel","sequence":"additional","affiliation":[{"name":"UMR STMS, IRCAM-CNRS Sorbonne Univ"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Simple and controllable music generation","volume-title":"Neurips","author":"Copet"},{"key":"ref2","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024"},{"key":"ref3","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref4","article-title":"Joint audio and symbolic conditioning for temporally controlled text-to-music generation","volume-title":"ISMIR","author":"Tal"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"ref6","article-title":"Singsong: Generating musical accompaniments from singing","author":"Donahue","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33584"},{"key":"ref9","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"ICLR","author":"Mariani"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"ref11","article-title":"Wavenet: A generative model for raw audio","author":"van den Oord","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref13","article-title":"High fidelity neural audio compression","volume-title":"TMLR","author":"D\u00e9fossez"},{"key":"ref14","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref15","article-title":"An independence-promoting loss for music generation with language models","author":"Lemercier","year":"2024"},{"key":"ref16","article-title":"Masked audio generation using a single non-autoregressive transformer","volume-title":"ICLR","author":"Ziv"},{"key":"ref17","article-title":"Vampnet: Music generation via masked acoustic token mod-eling","author":"Garcia","year":"2023"},{"key":"ref18","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447265"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref22","article-title":"Zero-shot unsupervised and text-based audio editing using ddpm inversion","volume-title":"ICML","author":"Manor"},{"key":"ref23","article-title":"Ditto: Diffusion inference-time t-optimization for music generation","author":"Novack","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446869"},{"key":"ref26","article-title":"Audio conditioning for music generation via discrete bottleneck features","volume-title":"ISMIR","author":"Rouard"},{"key":"ref27","article-title":"Instruct-musicgen: Unlocking text-to-music editing for music language models via instruction tuning","author":"Zhang","year":"2024"},{"key":"ref28","article-title":"Diff-a-riff: Musical accompaniment co-creation via latent diffusion models","author":"Nistal","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095889"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973795"},{"key":"ref32","article-title":"mir_eval: A transparent implementation of common mir metrics","volume-title":"Proceedings - 15th International Society for Music Information Retrieval Conference (ISMIR 2014)","author":"Raffel"},{"key":"ref33","article-title":"Pesto: Pitch estimation with self-supervised transposition-equivariant objective","volume-title":"Proceedings of the 24th International Society for Music Information Retrieval Conference, ISMIR 2023","author":"Riou"},{"key":"ref34","volume-title":"Twentieth-Century Harmony","author":"Persichetti","year":"1961"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"}],"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\/10890052.pdf?arnumber=10890052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:04Z","timestamp":1774416124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890052","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}