{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:44:26Z","timestamp":1768549466996,"version":"3.49.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2024,12,8]]},"DOI":"10.1109\/gcwkshp64532.2024.11101684","type":"proceedings-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T17:51:39Z","timestamp":1755021099000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Generative Semantic Communication for Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Zheng","sequence":"first","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinke","family":"Ren","sequence":"additional","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shenzhen Future Network of Intelligence Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gui","family":"Gui","sequence":"additional","affiliation":[{"name":"Central South University,School of Automation,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2021.9663101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3386052"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10000901"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2300553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620755"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/wcnc57260.2024.10571010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3240969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref13","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023"},{"key":"ref14","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Popov"},{"key":"ref15","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3265201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref18","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Casanova"}],"event":{"name":"2024 IEEE Globecom Workshops (GC Wkshps)","location":"Cape Town, South Africa","start":{"date-parts":[[2024,12,8]]},"end":{"date-parts":[[2024,12,12]]}},"container-title":["2024 IEEE Globecom Workshops (GC Wkshps)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099626\/11099614\/11101684.pdf?arnumber=11101684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T05:46:39Z","timestamp":1755063999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11101684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/gcwkshp64532.2024.11101684","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}