{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:18Z","timestamp":1774419738349,"version":"3.50.1"},"reference-count":46,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889289","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning"],"prefix":"10.1109","author":[{"given":"Jisi","family":"Zhang","sequence":"first","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo Peso","family":"Parada","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md","family":"Asif Jalal","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthikeyan","family":"Saravanan","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref6","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024"},{"key":"ref7","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"key":"ref8","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref9","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","article-title":"MuLan: A joint embedding of music audio and natural language","volume-title":"International Society for Music Information Retrieval Conference","author":"Huang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref12","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"North American Chapter of the Association for Computational Linguistics"},{"key":"ref13","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097117"},{"key":"ref15","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734763"},{"key":"ref17","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"issue":"70","key":"ref19","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","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"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref22","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref23","article-title":"Whitening sentence representations for better semantics and faster retrieval","author":"Su","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref28","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref29","first-page":"21696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref31","article-title":"The MTG-Jamendo dataset for automatic music tagging","volume-title":"International Conference on Machine Learning","author":"Bogdanov"},{"key":"ref32","article-title":"FMA: A dataset for music analysis","volume-title":"International Society for Music Information Retrieval Conference","author":"Defferrard"},{"key":"ref33","article-title":"Pond5","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"ref36","article-title":"AudioLDM training, finetuning, inference and evaluation","year":"2023"},{"key":"ref37","article-title":"LAION-AI\/CLAP","year":"2023"},{"key":"ref38","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref42","first-page":"2350","article-title":"Fr\u00e9chet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume-title":"Proc. Interspeech","author":"Roblek"},{"key":"ref43","article-title":"Audio generation evaluation","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref46","article-title":"CoLLAT: On adding fine-grained audio understanding to language models using token-level locked-language tuning","author":"Silva","year":"2023","journal-title":"Neural Information Processing Systems"}],"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\/10889289.pdf?arnumber=10889289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:23Z","timestamp":1774416263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889289","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}