{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:27:39Z","timestamp":1776886059089,"version":"3.51.2"},"reference-count":25,"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"}],"funder":[{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890827","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["PicoAudio: Enabling Precise Temporal Controllability in Text-to-Audio Generation"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Xie","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kreuk"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref4","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref6","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"},{"key":"ref7","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref8","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29773"},{"key":"ref12","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448441"},{"key":"ref16","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3443614"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref22","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832255"}],"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\/10890827.pdf?arnumber=10890827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:29Z","timestamp":1774416329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890827","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}