{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T18:38:06Z","timestamp":1782239886534,"version":"3.54.5"},"reference-count":34,"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\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","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\/icassp49660.2025.10890587","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":17,"title":["Temporally Aligned Audio for Video with Autoregression"],"prefix":"10.1109","author":[{"given":"Ilpo","family":"Viertola","sequence":"first","affiliation":[{"name":"Tampere University,Computing Sciences,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir","family":"Iashin","sequence":"additional","affiliation":[{"name":"Tampere University Engineering Science, University of Oxford,Computing Sciences,Oxford,United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esa","family":"Rahtu","sequence":"additional","affiliation":[{"name":"Tampere University,Computing Sciences,Tampere,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref2","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume-title":"NeurIPS","author":"Luo"},{"key":"ref3","article-title":"Frieren: Efficient video-to-audio generation with rectified flow matching","author":"Wang","year":"2024"},{"key":"ref4","article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/mlsp58920.2024.10734721"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref10","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref11","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177894"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.3009820"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33934"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref23","article-title":"Simple and controllable music generation","volume-title":"NeurIPS","author":"Copet"},{"key":"ref24","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref25","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref26","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref27","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"ref28","article-title":"Audiogen: Textually guided audio generation","volume-title":"ICLR","author":"Kreuk"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.633"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref31","article-title":"Sparse in space and time: Audio-visual synchronisation with trainable selectors","author":"Iashin","year":"2022","journal-title":"BMVC"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"}],"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\/10890587.pdf?arnumber=10890587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:15Z","timestamp":1774416255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890587","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}