{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:52:39Z","timestamp":1779202359848,"version":"3.51.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62201505"],"award-info":[{"award-number":["62201505"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1909207"],"award-info":[{"award-number":["U1909207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Key Project of National Natural Science Foundation of China-Regional Innovation Development Joint Foundation","doi-asserted-by":"publisher","award":["U21A20456"],"award-info":[{"award-number":["U21A20456"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"5G Open Laboratory of Hangzhou Future Sci-Tech City"},{"DOI":"10.13039\/501100007040","name":"Singapore University of Technology and Design (SUTD)-Zhejiang University (ZJU) Design and Entrepreneurship Alliance","doi-asserted-by":"publisher","award":["SUTD-ZJU (VP) 202102"],"award-info":[{"award-number":["SUTD-ZJU (VP) 202102"]}],"id":[{"id":"10.13039\/501100007040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021FZZX001-20"],"award-info":[{"award-number":["2021FZZX001-20"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/jsac.2022.3221952","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T20:38:13Z","timestamp":1668631093000},"page":"245-259","source":"Crossref","is-referenced-by-count":196,"title":["Semantic-Preserved Communication System for Highly Efficient Speech Transmission"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1307-2575","authenticated-orcid":false,"given":"Tianxiao","family":"Han","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4747-9410","authenticated-orcid":false,"given":"Qianqian","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9160-048X","authenticated-orcid":false,"given":"Zhiguo","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1505-6766","authenticated-orcid":false,"given":"Shibo","family":"He","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2346-6228","authenticated-orcid":false,"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref33","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946971"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref37","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","author":"park","year":"2019","journal-title":"G2pe"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/PROC.1973.9030","article-title":"The Viterbi algorithm","volume":"61","author":"forney","year":"1993","journal-title":"Proc IEEE"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS56560.2022.9940401"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461983"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2018.8445924"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036968"},{"key":"ref14","article-title":"Task-oriented multi-user semantic communications","author":"xie","year":"2021","journal-title":"arXiv 2112 10255"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3136045"},{"key":"ref16","article-title":"DeepWiVe: Deep-learning-aided wireless video transmission","author":"tung","year":"2021","journal-title":"arXiv 2111 13034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/frcmn.2021.734402"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00041-3"},{"key":"ref4","author":"carnap","year":"1952","journal-title":"An Outline of A Theory of Semantic Information"},{"key":"ref27","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","author":"shannon","year":"1949","journal-title":"The Mathematical Theory of Communication"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/NSW.2011.6004632"},{"key":"ref29","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/B:MIND.0000021684.50925.c9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2013.07.013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3071210"},{"key":"ref1","article-title":"Semantic communications: Principles and challenges","author":"qin","year":"2021","journal-title":"arXiv 2201 01389"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3090048"},{"key":"ref20","article-title":"Semantic communications for speech recognition","author":"weng","year":"2021","journal-title":"arXiv 2107 11190"},{"key":"ref22","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","author":"bazzi","year":"2002","journal-title":"Modelling out-of-vocabulary words for robust speech recognition"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref25","article-title":"Semantic-aware speech to text transmission with redundancy removal","author":"han","year":"2022","journal-title":"arxiv 2202 03211"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9991040\/09953316.pdf?arnumber=9953316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:22:51Z","timestamp":1673896971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":42,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2022.3221952","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}