{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:07Z","timestamp":1761894547556,"version":"build-2065373602"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209133","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["An Investigation on Audio-Prompt and Structure Guided Long-Duration Music Generation Based on Diffusion Models"],"prefix":"10.1109","author":[{"given":"Ziyu","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zilu","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Ma","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref1"},{"key":"ref2","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"article-title":"Mo\\^ usai: Text-to-music generation with long-context latent diffusion","year":"2023","author":"Schneider","key":"ref4"},{"article-title":"Noise2music: Text-conditioned music generation with diffusion models","year":"2023","author":"Huang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1126"},{"key":"ref7","article-title":"Efficient neural music generation","volume":"36","author":"Lam","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.4926438"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"issue":"8","key":"ref10","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"article-title":"Long-form music generation with latent diffusion","year":"2024","author":"Evans","key":"ref11"},{"article-title":"Fast timing-conditioned latent audio diffusion","year":"2024","author":"Evans","key":"ref12"},{"key":"ref13","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2168211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"ref18","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Zero-shot unsupervised and text-based audio editing using ddpm inversion","year":"2024","author":"Manor","key":"ref19"},{"article-title":"Progressive distillation for fast sampling of diffusion models","year":"2022","author":"Salimans","key":"ref20"},{"article-title":"Score-based generative modeling through stochastic differential equations","year":"2020","author":"Song","key":"ref21"},{"article-title":"Denoising diffusion implicit models","year":"2020","author":"Song","key":"ref22"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"The song describer dataset: a corpus of audio captions for music-and-language evaluation","year":"2023","author":"Manco","key":"ref24"},{"article-title":"Fr\\\u2019echet audio distance: A metric for evaluating music enhancement algorithms","year":"2018","author":"Kilgour","key":"ref25"},{"article-title":"Audioldm: Text-to-audio generation with latent diffusion models","year":"2023","author":"Liu","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209133.pdf?arnumber=11209133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:35Z","timestamp":1761888635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209133","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}