{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T02:02:44Z","timestamp":1782352964640,"version":"3.54.5"},"reference-count":34,"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"}],"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"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889094","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":1,"title":["MotionComposer: Enhancing Rhythmic Music Generation with Adaptive Retrieval Reference"],"prefix":"10.1109","author":[{"given":"Jinting","family":"Wang","sequence":"first","affiliation":[{"name":"Artificial Intelligence HKUST (GZ),Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"Artificial Intelligence HKUST (GZ),Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab Tencent,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref2","article-title":"Efficient neural music generation","volume":"36","author":"Lam","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447027"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446869"},{"key":"ref5","article-title":"Long-term rhythmic video soundtracker","volume-title":"International Conference on Machine Learning (ICML)","author":"Yu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3405734"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref8","first-page":"29258","article-title":"How does it sound?","volume":"34","author":"Su","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref10","article-title":"Discrete contrastive diffusion for cross-modal music and image generation","author":"Zhu","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687562"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-65647-7_7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657957"},{"key":"ref16","article-title":"Seakr: Self-aware knowledge retrieval for adaptive retrieval augmented generation","author":"Yao","year":"2024"},{"key":"ref17","article-title":"Ctrla: Adaptive retrieval-augmented generation via probe-guided control","author":"Liu","year":"2024"},{"key":"ref18","article-title":"Retrieve only when it needs: Adaptive retrieval augmentation for hallucination mitigation in large language models","author":"Ding","year":"2024"},{"key":"ref19","article-title":"Dance2music: Automatic dance-driven music generation","author":"Aggarwal","year":"2021"},{"key":"ref20","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref21","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","author":"Chen","year":"2022"},{"key":"ref22","article-title":"Lift yourself up: Retrieval-augmented text generation with self-memory","volume":"36","author":"Cheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591687"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"ref26","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34743"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4135\/9781446251409.n4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref30","first-page":"49","article-title":"Evaluating the online capabilities of onset detection methods","volume-title":"ISMIR","author":"B\u00f6ck"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref33","article-title":"Archisound: Audio generation with diffusion","author":"Schneider","year":"2023"},{"key":"ref34","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"}],"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\/10889094.pdf?arnumber=10889094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:00Z","timestamp":1774416360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889094","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}