{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:18Z","timestamp":1774419378347,"version":"3.50.1"},"reference-count":38,"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\/icassp49660.2025.10887957","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":0,"title":["FCConDubber: Fine And Coarse Grained Prosody Alignment For Expressive Video Dubbing via Contrastive Audio-Motion Pretraining"],"prefix":"10.1109","author":[{"given":"Qiulin","family":"Li","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}]},{"given":"Zhichao","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}]},{"given":"Hanwei","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}]},{"given":"Xin","family":"Dong","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}]},{"given":"Qun","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"16582","article-title":"Neural dubber: Dubbing for videos according to scripts","volume":"34","author":"Hu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref5","first-page":"13963","article-title":"Portaspeech: Portable and high-quality generative text-to-speech","volume":"34","author":"Ren","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746421"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01033"},{"key":"ref9","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume":"32","author":"Li","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26523"},{"key":"ref12","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref13","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445962"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389638"},{"key":"ref18","article-title":"Audio language modeling using perceptually-guided discrete representations","author":"Kreuk","year":"2022"},{"key":"ref19","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref24","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref25","first-page":"1914","article-title":"Infonce loss provably learns cluster-preserving representations","volume-title":"The Thirty Sixth Annual Conference on Learning Theory","author":"Parulekar"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01617"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref30","first-page":"2758","article-title":"Lip to speech synthesis with visual context attentional gan","volume":"34","author":"Kim","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548081"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref33","article-title":"Vocos: Closing the gap between time-domain and fourierbased neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960497"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref38","first-page":"1455","article-title":"An analysis of the t-sne algorithm for data visualization","volume-title":"Conference on learning theory","author":"Arora"}],"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\/10887957.pdf?arnumber=10887957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:34Z","timestamp":1774416154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887957","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}