{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:39:20Z","timestamp":1772933960228,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402273","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"4989-4995","source":"Crossref","is-referenced-by-count":0,"title":["A Modular Approach to Music Generation: Adding Music Controls to Neural Audio Compression Models"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Faronbi","sequence":"first","affiliation":[{"name":"New York University,Music and Audio Research Laboratory,New York,USA"}]},{"given":"Peter","family":"Traver","sequence":"additional","affiliation":[{"name":"New York University,Music and Audio Research Laboratory,New York,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1117\/12.234776"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025099"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1178723.1178730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref5","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref7","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"ref9","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Ddsp: Differentiable digital signal processing","author":"Engel","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461711"},{"key":"ref13","article-title":"Timbretron: A wavenet (cyclegan (cqt (audio))) pipeline for musical timbre transfer","author":"Huang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Cyclegan, a master of steganography","author":"Chu","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414235"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019642"},{"issue":"7\/8","key":"ref17","first-page":"562","article-title":"Audio pitch shifting using the constant-q transform","volume":"61","author":"Sch\u00f6rkhuber","year":"2013","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.1999.810857"},{"key":"ref19","article-title":"Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling","author":"Ji","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.937"},{"key":"ref21","article-title":"Snac: Multi-scale neural audio codec","author":"Siuzdak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref23","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref27","article-title":"Vampnet: Music generation via masked acoustic token modeling","author":"Flores Garcia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Generating sample-based musical instruments using neural audio codec language models","author":"Nercessian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Efficient neural music generation","volume":"36","author":"Lam","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref33","article-title":"Joint audio and symbolic conditioning for temporally controlled text-to-music generation","author":"Tal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Ditto: Diffusion inference-time t-optimization for music generation","author":"Novack","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Ditto-2: Distilled diffusion inference-time toptimization for music generation","author":"Novack","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","author":"Forsgren","year":"2022","journal-title":"Riffusion-stable diffusion for realtime music generation"},{"key":"ref38","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"Forty-first International Conference on Machine Learning","author":"Evans"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"ref41","article-title":"Fr \u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref44","article-title":"Video-guided text-to-music generation using public domain movie collections","author":"Kim","year":"2025","journal-title":"ISMIR 2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402273.pdf?arnumber=11402273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:56:02Z","timestamp":1772866562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402273","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}