{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:16Z","timestamp":1784268376123,"version":"3.55.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447265","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1206-1210","source":"Crossref","is-referenced-by-count":71,"title":["MusicLDM: Enhancing Novelty in text-to-music Generation Using Beat-Synchronous mixup Strategies"],"prefix":"10.1109","author":[{"given":"Ke","family":"Chen","sequence":"first","affiliation":[{"name":"University of California San Diego (UCSD)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusong","family":"Wu","sequence":"additional","affiliation":[{"name":"Mila, Quebec Artificial Intelligence Institute, Universite de Montreal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haohe","family":"Liu","sequence":"additional","affiliation":[{"name":"Centre for Vision Speech and Signal Processing, University of Surrey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marianna","family":"Nezhurina","sequence":"additional","affiliation":[{"name":"LAION"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taylor","family":"Berg-Kirkpatrick","sequence":"additional","affiliation":[{"name":"University of California San Diego (UCSD)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shlomo","family":"Dubnov","sequence":"additional","affiliation":[{"name":"University of California San Diego (UCSD)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70163-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780190226992.013.23"},{"key":"ref3","article-title":"Turn ideas into music with musiclm","author":"Yim"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref7","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023"},{"key":"ref8","article-title":"Mubert: A simple notebook demonstrating prompt-based music generation"},{"key":"ref9","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref10","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref11","article-title":"Riffusion - Stable diffusion for real-time music generation","author":"Forsgren","year":"2022"},{"key":"ref12","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00586"},{"key":"ref14","article-title":"Extracting training data from diffusion models","author":"Carlini","year":"2023"},{"key":"ref15","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref17","article-title":"Auto-encoding variational bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref18","first-page":"17022","article-title":"HifiGAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref20","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref23","article-title":"Dif-fwave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref24","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref25","article-title":"Beat transformer: Demixed beat and downbeat tracking with dilated self-attention","volume-title":"Proc. ISMIR","author":"Zhao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447265.pdf?arnumber=10447265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:33:49Z","timestamp":1722576829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447265","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}