{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:04:38Z","timestamp":1781193878597,"version":"3.54.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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","doi-asserted-by":"publisher","award":["62122095"],"award-info":[{"award-number":["62122095"]}],"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":["62341201"],"award-info":[{"award-number":["62341201"]}],"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":["62072472"],"award-info":[{"award-number":["62072472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020721","name":"Guoqiang Institute, Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020721","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tmc.2024.3419170","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T18:27:51Z","timestamp":1719426471000},"page":"12848-12865","source":"Crossref","is-referenced-by-count":12,"title":["UltraSR: Silent Speech Reconstruction via Acoustic Sensing"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8481-2644","authenticated-orcid":false,"given":"Yongjian","family":"Fu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9727-1434","authenticated-orcid":false,"given":"Shuning","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linghui","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2782-183X","authenticated-orcid":false,"given":"Ju","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6717-461X","authenticated-orcid":false,"given":"Yaoxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.445"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738568"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1119-1"},{"key":"ref4","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461596"},{"key":"ref8","first-page":"593","article-title":"We can hear you with WifI!.(2014)","volume-title":"Proc. 20th Annu. Int. Conf. Mobile Comput. Netw.","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057099"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3411830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3448087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3381008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2008.11.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568530"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3643546"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3191768"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486283"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3478093"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448626"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3145856"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133962"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3369812"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.02.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/S0952675700001019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.55.090902.142028"},{"key":"ref27","first-page":"1","article-title":"Tongue and lip motion patterns in voiced, whispered, and silent vowel production","volume-title":"Proc. Int. Congr. Phonetic Sci.","author":"Teplansky"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3051665"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858580"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3075764"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","volume-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"ref33","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref35","article-title":"Unsupervised machine translation using monolingual corpora only","author":"Lample","year":"2017"},{"key":"ref36","article-title":"Unsupervised neural machine translation","author":"Artetxe","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1549"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2323"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3517257"},{"key":"ref41","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"issue":"5","key":"ref42","article-title":"Conditional generative adversarial nets for convolutional face generation","volume":"2014","author":"Gauthier","year":"2014","journal-title":"Class Project Stanford CS231N, Convolutional Neural Netw. Vis. Recognit., Winter Semester"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296650"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683799"},{"key":"ref46","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3424116"},{"key":"ref48","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Koch"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref50","article-title":"A guide to convolution arithmetic for deep learning","author":"Dumoulin","year":"2016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210312"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1078"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1002\/9781119540618.ch20"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref63","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3448100"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3550318"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625798"},{"key":"ref68","article-title":"A cross-modal approach to silent speech with LLM-enhanced recognition","author":"Benster","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483251"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3550329"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1226"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10746253\/10572342.pdf?arnumber=10572342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:28:56Z","timestamp":1732667336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10572342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":70,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3419170","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}