{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:00:13Z","timestamp":1778605213531,"version":"3.51.4"},"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\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","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\/icassp49660.2025.10889473","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":9,"title":["Sound-VECaps: Improving Audio Generation with Visually Enhanced Captions"],"prefix":"10.1109","author":[{"given":"Yi","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongya","family":"Jia","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Zhuang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiyuan","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"issue":"1","key":"ref2","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"},{"issue":"3","key":"ref3","first-page":"8","article-title":"Improving image generation with better captions","volume-title":"Computer Science","volume":"2","author":"Betker","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref11","article-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"Liu","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref13","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":"ref14","article-title":"AudioLDM: Text-to-Audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref15","article-title":"Valor: Vision-audio-language omni-perception pretraining model and dataset","author":"Chen","year":"2023"},{"key":"ref16","first-page":"38 728","article-title":"mPLUG-2: A modularized multi-modal foundation model across text, image and video","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref17","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref18","article-title":"CogVLM: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446672"},{"key":"ref20","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref21","article-title":"AudioGen: textually guided audio generation","volume-title":"International Conference on Learning Representations","author":"Kreuk"},{"key":"ref22","first-page":"17 022","article-title":"HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Kong"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734763"}],"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\/10889473.pdf?arnumber=10889473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:06Z","timestamp":1774416066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889473","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}