{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:00:25Z","timestamp":1775199625387,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434607","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Controllable Music Generation with Latent Rectified Flow Guided by Rhythm and Harmony"],"prefix":"10.1109","author":[{"given":"Haibin","family":"Yu","sequence":"first","affiliation":[{"name":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"}]},{"given":"Jiayi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"}]},{"given":"Zhiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group"}]},{"given":"Huijia","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ant Group"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2301.11325"},{"key":"ref2","article-title":"Simple and controllable music generation","volume-title":"Proc. NeurIPS","author":"Copet"},{"key":"ref3","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref6","article-title":"Fast timingconditioned latent audio diffusion","volume-title":"Proc. ICML","author":"Evans"},{"key":"ref7","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024","journal-title":"arXiv preprint arXiv:2404.10301"},{"key":"ref8","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv:2209.03003"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref10","article-title":"Frieren: Efficient video-to-audio generation network with rectified flow matching","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445948"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447822"},{"key":"ref13","article-title":"Splitmeanflow: Interval splitting consistency in few-step generative modeling","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv:2507.16884"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"ref16","article-title":"Joint audio and symbolic conditioning for temporally controlled text-to-music generation","author":"Tal","year":"2024","journal-title":"arXiv preprint arXiv:2406.10970"},{"key":"ref17","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations","author":"Kingma"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref20","article-title":"Rfwave: Multi-band rectified flow for audio waveform reconstruction","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref21","article-title":"Flashaudio: Rectified flows for fast and high-fidelity text-to-audio generation","author":"Liu","year":"2024"},{"key":"ref22","article-title":"Flux that plays music","author":"Fei","year":"2024","journal-title":"arXiv preprint arXiv:2409.00587"},{"key":"ref23","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Esser"},{"key":"ref24","first-page":"146","article-title":"Audio conditioning for music generation via discrete bottleneck features","author":"Rouard","year":"2024","journal-title":"ISMIR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3507553"},{"key":"ref26","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"International Conference on Learning Representations","author":"Salimans"},{"key":"ref27","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref28","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref29","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref30","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref32","article-title":"FMA: A dataset for music analysis","volume-title":"18th International Society for Music Information Retrieval Conference (ISMIR)","author":"Defferrard"},{"key":"ref33","article-title":"The MTG-Jamendo dataset for automatic music tagging","volume-title":"Proc. ICML","author":"Bogdanov"},{"key":"ref34","article-title":"Learning-based methods for comparing sequences, with applications to audio-to-midi alignment and matching","author":"Raffel","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2496-0_20"},{"key":"ref36","article-title":"The mtgjamendo dataset for automatic music tagging","volume-title":"Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML 2019)","author":"Bogdanov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888056"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref40","article-title":"Beatnet: Crnn and particle filtering for online joint beat downbeat and meter tracking","author":"Heydari","year":"2021"},{"key":"ref41","first-page":"135","article-title":"Approximate note transcription for the improved identification of difficult chords","author":"Mauch","year":"2010","journal-title":"ISMIR"},{"key":"ref42","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446663"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434607.pdf?arnumber=11434607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:11Z","timestamp":1775192231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434607","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}