{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:23:32Z","timestamp":1783182212493,"version":"3.54.6"},"reference-count":32,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890132","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":7,"title":["STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment"],"prefix":"10.1109","author":[{"given":"Yong","family":"Ren","sequence":"first","affiliation":[{"name":"Tencent AI Lab,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxing","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manjie","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Seattle,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"21 450","article-title":"Audioldm: text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Liu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680612"},{"key":"ref7","article-title":"Discriminator-guided cooperative diffusion for joint audio and video generation","author":"Hayakawa","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref10","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":"ref11","article-title":"Video-to-audio generation with hidden alignment","author":"Xu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_15"},{"key":"ref13","article-title":"Frieren: Efficient video-to-audio generation with rectified flow matching","author":"Wang","year":"2024"},{"key":"ref14","article-title":"Text-to-audio generation synchronized with videos","author":"Mo","year":"2024"},{"key":"ref15","article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00055"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref20","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"4","article-title":"Maximum filter vibrato suppression for onset detection","volume-title":"Proc. of the 16th Int. Conf. on Digital Audio Effects (DAFx). Maynooth, Ireland (Sept 2013)","volume":"7","author":"B\u00f6ck"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref23","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680692"},{"key":"ref27","article-title":"Controlnet-xs: Designing an efficient and effective architecture for controlling text-to-image diffusion models","author":"Zavadski","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-325"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"}],"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\/10890132.pdf?arnumber=10890132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:48Z","timestamp":1774416288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890132","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}