{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T09:03:28Z","timestamp":1780563808062,"version":"3.54.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB2904300"],"award-info":[{"award-number":["2023YFB2904300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293484"],"award-info":[{"award-number":["62293484"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62442106"],"award-info":[{"award-number":["62442106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/twc.2025.3534995","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T18:53:22Z","timestamp":1738695202000},"page":"3684-3697","source":"Crossref","is-referenced-by-count":12,"title":["Synchronous Multi-Modal Semantic Communication System With Packet-Level Coding"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2960-6919","authenticated-orcid":false,"given":"Yun","family":"Tian","sequence":"first","affiliation":[{"name":"School of Electronics, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7920-8035","authenticated-orcid":false,"given":"Jingkai","family":"Ying","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8507-3975","authenticated-orcid":false,"given":"Zhijin","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Electronics, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-9338","authenticated-orcid":false,"given":"Xiaoming","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3437730"},{"key":"ref2","article-title":"Semantic communications: Principles and challenges","author":"Qin","year":"2021","journal-title":"arXiv:2201.01389"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3656580"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461983"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3071210"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3180997"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221999"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2987203"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036955"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221977"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191354"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3136045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191326"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3369864"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2024.3374700"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.008.2200180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP58612.2023.10404655"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437917"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3364990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221953"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.598"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref26","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref28","article-title":"Interactive face video coding: A generative compression framework","author":"Chen","year":"2023","journal-title":"arXiv:2302.09919"},{"key":"ref29","article-title":"Real-time neural radiance talking portrait synthesis via audio-spatial decomposition","author":"Tang","year":"2022","journal-title":"arXiv:2211.12368"},{"key":"ref30","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023","journal-title":"arXiv:2310.11230"},{"key":"ref31","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02056"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","first-page":"16582","article-title":"Neural dubber: Dubbing for videos according to scripts","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Hu"},{"key":"ref36","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ren"},{"key":"ref37","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","volume":"33","author":"Kong"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2970707"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3240969"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.240"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/25.350282"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/10994789\/10872781.pdf?arnumber=10872781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:46:20Z","timestamp":1747071980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10872781\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":51,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/twc.2025.3534995","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}