{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:53:11Z","timestamp":1776887591493,"version":"3.51.2"},"reference-count":43,"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\/icassp49660.2025.10890309","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Hou","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shansong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mangsuo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref2","article-title":"Simple and controllable music generation","volume-title":"Proc. NeurIPS","author":"Copet"},{"key":"ref3","article-title":"Joint audio and symbolic conditioning for temporally controlled text-to-music generation","author":"Tal","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00146"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"ref6","article-title":"Diff-a-riff: Musical accompaniment co-creation via latent diffusion models","volume-title":"Proc. ISMIR","author":"Nistal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref8","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"Proc. ICLR","author":"Mariani"},{"key":"ref9","article-title":"Singsong: Generating musical accompaniments from singing","author":"Donahue","year":"2023"},{"key":"ref10","article-title":"Content-based controls for music large language modeling","author":"Lin","year":"2023"},{"key":"ref11","article-title":"DITTO: Diffusion inference-time T-optimization for music generation","volume-title":"Proc. ICML","author":"Novack"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27810"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"key":"ref15","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"Proc. ICML","author":"Evans"},{"key":"ref16","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.437"},{"key":"ref21","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97257-7_6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/864"},{"key":"ref25","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. ICLR","author":"Ho"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref30","article-title":"Pixart-\u03b4: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024"},{"key":"ref31","article-title":"DITTO-2: Distilled diffusion inference-time t-optimization for music generation","volume-title":"Proc. ISMIR","author":"Novack"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref33","article-title":"Deep salience representations for f0 estimation in polyphonic music","volume-title":"Proc. ISMIR","author":"Bittner"},{"key":"ref34","article-title":"Combining audio control and style transfer using latent diffusion","volume-title":"Proc. ISMIR","author":"Demerl\u00e9"},{"key":"ref35","article-title":"The MTG-Jamendo dataset for automatic music tagging","volume-title":"Proc. ICML","author":"Bogdanov"},{"key":"ref36","article-title":"FMA: A dataset for music analysis","volume-title":"Proc. ISMIR","author":"Defferrard"},{"key":"ref37","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proc. ISMIR","author":"Law"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56435-2_4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref40","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. ICML","author":"Tang"},{"key":"ref41","article-title":"The Song Describer dataset: A corpus of audio captions for music-and-language evaluation","volume-title":"Proc. NeurIPS","author":"Manco"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref43","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS","author":"Ho"}],"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\/10890309.pdf?arnumber=10890309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:23Z","timestamp":1774416383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890309","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}