{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:12:35Z","timestamp":1773843155166,"version":"3.50.1"},"reference-count":26,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003513","name":"University of Surrey","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003513","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\/icassp48485.2024.10447898","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"581-585","source":"Crossref","is-referenced-by-count":21,"title":["Retrieval-Augmented Text-to-Audio Generation"],"prefix":"10.1109","author":[{"given":"Yi","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Surrey,School of Computer Science and Electronic Engineering,UK"}]},{"given":"Haohe","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,School of Computer Science and Electronic Engineering,UK"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,School of Computer Science and Electronic Engineering,UK"}]},{"given":"Qiushi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Surrey,School of Computer Science and Electronic Engineering,UK"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,School of Computer Science and Electronic Engineering,UK"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,School of Computer Science and Electronic Engineering,UK"}]}],"member":"263","reference":[{"key":"ref1","article-title":"AudioLDM: Text-to-Audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref2","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref3","article-title":"WavJourney: Compositional audio creation with large language models","author":"Liu","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref5","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Kim"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289975"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596430"},{"key":"ref9","first-page":"864","article-title":"PixelSNAIL: An improved autoregressive generative model","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref10","article-title":"Taming visually guided sound generation","volume-title":"British Machine Vision Conference","author":"Iashin"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"issue":"1","key":"ref14","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":"Journal of Machine Learning Research"},{"key":"ref15","article-title":"Memory-driven text-to-image generation","volume-title":"British Machine Vision Conference","author":"Li"},{"key":"ref16","first-page":"15309","article-title":"Retrieval-augmented diffusion models","volume":"35","author":"Blattmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"KNN-diffusion: Image generation via large-scale retrieval","volume-title":"International Conference on Learning Representations","author":"Sheynin"},{"key":"ref18","article-title":"Re-Imagen: Retrieval-augmented text-to-image generator","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref19","first-page":"231","article-title":"Text-driven Foley sound generation with latent diffusion model","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop","author":"Yuan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref21","article-title":"Masked autoencoders that listen","author":"Xu","year":"2022"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref23","article-title":"AudioGen: textually guided audio generation","volume-title":"International Conference on Learning Representations","author":"Kreuk"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","article-title":"TAU Urban Acoustic Scenes 2019, Development dataset","author":"Heittola","year":"2019"},{"key":"ref26","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\/10447898.pdf?arnumber=10447898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:49:36Z","timestamp":1722574176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447898","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}