{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:31Z","timestamp":1774419391703,"version":"3.50.1"},"reference-count":37,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","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\/icassp49660.2025.10887573","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":2,"title":["TA-V2A: Textually Assisted Video-to-Audio Generation"],"prefix":"10.1109","author":[{"given":"Yuhuan","family":"You","sequence":"first","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]},{"given":"Xihong","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]},{"given":"Tianshu","family":"Qu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref2","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"},{"key":"ref3","article-title":"Text-to-audio generation synchronized with videos","author":"Mo","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-93806-1_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177894"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_15"},{"key":"ref12","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume":"36","author":"Luo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Video-to-audio generation with hidden alignment","author":"Xu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33934"},{"key":"ref15","article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024"},{"key":"ref16","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023"},{"key":"ref17","article-title":"Any-to-any generation via composable diffusion","volume":"36","author":"Tang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1771"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref30","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref31","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446058"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco63174.2024.10714935"},{"key":"ref37","article-title":"ITU-T Recommendation P.800: Methods for Subjective Determination of Transmission Quality","year":"1996"}],"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\/10887573.pdf?arnumber=10887573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:38Z","timestamp":1774416158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887573","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}