{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:54:26Z","timestamp":1753602866652,"version":"3.37.3"},"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"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447122","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6980-6984","source":"Crossref","is-referenced-by-count":2,"title":["Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models"],"prefix":"10.1109","author":[{"given":"Emilian","family":"Postolache","sequence":"first","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giorgio","family":"Mariani","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Cosmo","sequence":"additional","affiliation":[{"name":"Ca’ Foscari University of Venice"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[{"name":"Queen Mary University of London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Rodol\u00e0","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural discrete representation learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","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":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song","key":"ref4"},{"journal-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref5"},{"journal-title":"Simple and controllable music generation","year":"2023","author":"Copet","key":"ref6"},{"journal-title":"Vampnet: Music generation via masked acoustic token modeling","year":"2023","author":"Garcia","key":"ref7"},{"journal-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","year":"2023","author":"Schneider","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"issue":"1","key":"ref10","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"journal-title":"Multi-source diffusion models for simultaneous music generation and separation","year":"2023","author":"Mariani","key":"ref14"},{"journal-title":"Audit: Audio editing by following instructions with latent diffusion models","year":"2023","author":"Wang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/645"},{"journal-title":"Singsong: Generating musical accompaniments from singing","year":"2023","author":"Donahue","key":"ref17"},{"article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","key":"ref18"},{"journal-title":"Stay on topic with classifier-free guidance","year":"2023","author":"Sanchez","key":"ref19"},{"key":"ref20","first-page":"4724","article-title":"Source separation with deep generative priors","volume-title":"International Conference on Machine Learning","author":"Jayaram"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"article-title":"The mtg-jamendo dataset for automatic music tagging","volume-title":"International Conference on Machine Learning","author":"Bogdanov","key":"ref22"},{"key":"ref23","first-page":"5775","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"journal-title":"Gass: Generalizing audio source separation with large-scale data","year":"2023","author":"Pons","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747076"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10447122.pdf?arnumber=10447122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:53:41Z","timestamp":1722574421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447122","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}