{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:02:02Z","timestamp":1776888122132,"version":"3.51.2"},"reference-count":19,"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\/icassp49660.2025.10889879","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["AudioTime: A Temporally-aligned Audio-text Benchmark Dataset"],"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":"International Conference on Learning Representations (ICLR)","author":"Kreuk"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref3","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning (ICML)","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref7","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning (ICML)","author":"Huang"},{"key":"ref8","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29773"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"key":"ref11","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Kim"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448441"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3443614"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref17","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1614"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"}],"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\/10889879.pdf?arnumber=10889879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:00Z","timestamp":1774416180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889879","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}