{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:36:58Z","timestamp":1769751418793,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["62293484,61925105"],"award-info":[{"award-number":["62293484,61925105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,9]]},"DOI":"10.1109\/icc51166.2024.10622487","type":"proceedings-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T15:34:42Z","timestamp":1724168082000},"page":"3396-3401","source":"Crossref","is-referenced-by-count":5,"title":["Synchronous Semantic Communications for Video and Speech"],"prefix":"10.1109","author":[{"given":"Yun","family":"Tian","sequence":"first","affiliation":[{"name":"School of Electronics, Peking University,Beijing,China"}]},{"given":"Jingkai","family":"Ying","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electrical Engineering,Beijing,China"}]},{"given":"Zhijin","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electrical Engineering,Beijing,China"}]},{"given":"Ye","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Electronics, Peking University,Beijing,China"}]},{"given":"Xiaoming","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electrical Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Semantic communications: principles and challenges","author":"Qin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Foundations and recent trends in multimodal machine learning: principles, challenges, and open questions","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036955"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3240969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191326"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.008.2200180"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221968"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221953"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221977"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087240"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.598"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref17","article-title":"Real-time neural radiance talking portrait synthesis via audio-spatial decomposition","volume-title":"arXiv preprint","author":"Tang","year":"2022"},{"key":"ref18","article-title":"Zipformer: a faster and better encoder for automatic speech recognition","author":"Yao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02056"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","first-page":"16582","article-title":"Neural dubber: dubbing for videos according to scripts","volume":"34","author":"Hu","year":"2021","journal-title":"Adv. Neural Inf. Proces. Syst. (NIPS)"},{"key":"ref24","article-title":"FastSpeech 2: fast and high-quality end-to-end text to speech","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Ren","year":"2021"},{"key":"ref25","first-page":"17022","article-title":"HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Adv. Neural Inf. Proces. Syst. (NIPS)","volume":"33","author":"Kong","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"}],"event":{"name":"ICC 2024 - IEEE International Conference on Communications","location":"Denver, CO, USA","start":{"date-parts":[[2024,6,9]]},"end":{"date-parts":[[2024,6,13]]}},"container-title":["ICC 2024 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10622104\/10622158\/10622487.pdf?arnumber=10622487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T20:15:10Z","timestamp":1724962510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10622487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icc51166.2024.10622487","relation":{},"subject":[],"published":{"date-parts":[[2024,6,9]]}}}