{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:07Z","timestamp":1784041087266,"version":"3.55.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"BK21 FOUR"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3126925","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T23:23:15Z","timestamp":1637191395000},"page":"3654-3667","source":"Crossref","is-referenced-by-count":20,"title":["Speech Reconstruction With Reminiscent Sound Via Visual Voice Memory"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-1000","authenticated-orcid":false,"given":"Joanna","family":"Hong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-0018","authenticated-orcid":false,"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8467-3576","authenticated-orcid":false,"given":"Se Jin","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1109\/TASLP.2019.2960721","article-title":"Non-parallel sequence-to-sequence voice conversion with disentangled linguistic and speaker representations","volume":"28","author":"zhang","year":"2019","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4324\/9780203098752"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414040"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref35","article-title":"Wavenet: A generative model for raw","author":"oord","year":"2016"},{"key":"ref34","first-page":"14?910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","first-page":"114","article-title":"Improved closed set text-independent speaker identification by combining MFCC with evidence from flipped filter banks","volume":"4","author":"chakroborty","year":"2007","journal-title":"Int J Signal Process"},{"key":"ref62","first-page":"214","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","first-page":"3918","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","article-title":"Fast wavenet generation algorithm","author":"paine","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2018.00-19"},{"key":"ref64","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.330110023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3269"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2716178"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241911"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref54","first-page":"192","article-title":"S3FD: Single shot scale-invariant face detector","author":"zhang","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref53","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref11","article-title":"LipNet: End-to-end sentence-level lipreading","author":"assael","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref12","article-title":"Lip-reading with hierarchical pyramidal convolution and self-attention","author":"chen","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref15","article-title":"Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading","author":"weng","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref16","article-title":"Multi-grained spatio-temporal modeling for lip-reading","author":"wang","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414353"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.922789"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.08.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-019-09653-z"},{"key":"ref49","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc Proc 27th Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref46","first-page":"2440","article-title":"End-to-end memory networks","volume":"28","author":"sukhbaatar","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref48","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00429"},{"key":"ref43","article-title":"Learning to remember rare events","author":"kaiser","year":"2017","journal-title":"Proc Int Conf Learn Representations (ICLR)"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09618777.pdf?arnumber=9618777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:53Z","timestamp":1652194433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9618777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3126925","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}