{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:34:57Z","timestamp":1790620497390,"version":"4.1.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"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":[[2021,5]]},"DOI":"10.1109\/iscas51556.2021.9401485","type":"proceedings-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T21:33:36Z","timestamp":1619559216000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["EMA2S: An End-to-End Multimodal Articulatory-to-Speech System"],"prefix":"10.1109","author":[{"given":"Yu-Wen","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuo-Hsuan","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shang-Yi","family":"Chuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Sherman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xugang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Texture synthesis using convolutional neural networks","author":"gatys","year":"2015","journal-title":"Proc NIPS"},{"key":"ref38","article-title":"A study of incorporating articulatory movement information in speech enhancement","author":"chen","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1617"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.006"},{"key":"ref30","article-title":"Transfer learning from speech synthesis to voice conversion with non-parallel training data","author":"zhang","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305052"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756818"},{"key":"ref35","article-title":"Multimodal electropalatography-audio speech enhancement","author":"chen","year":"0","journal-title":"submitted to ICASSP 2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3000968"},{"key":"ref10","article-title":"Determination of the vocal tract spectrum from the articulatory movements based on the search of an articulatory-acoustic database","author":"kaburagi","year":"1998","journal-title":"Proc ICSLP"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.131"},{"key":"ref11","article-title":"Mapping from articulatory movements to vocal tract spectrum with gaussian mixture model for articulatory speech synthesis","author":"toda","year":"2004","journal-title":"Proc SSW5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.02.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-715"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref18","article-title":"Wavenet: a generative model for raw audio","author":"oord","year":"2016","journal-title":"Proc SSW9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref28","article-title":"Voice transformer network: sequence-to-sequence voice conversion using transformer with text-to-speech pretraining","author":"huang","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738568"},{"key":"ref27","article-title":"Text-informed speech enhancement with deep neural networks","author":"kinoshita","year":"2015","journal-title":"Proc Inter-speech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73279-2_87"},{"key":"ref6","article-title":"Learning mixed acoustic\/articulatory models for disabled speech","author":"rudzicz","year":"2010","journal-title":"Proc NIPS"},{"key":"ref29","article-title":"End-to-end voice conversion via cross-modal knowledge distillation for dysarthric speech reconstruction","author":"wang","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1703"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.02.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.2002.0166"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-272","article-title":"Cross linguistic comparison of Mandarin and English EMA articulatory data","author":"li","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054233"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1250\/ast.20.199"},{"key":"ref24","article-title":"Speech recognition (version 3.8)","author":"zhang","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.1377633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref44","first-page":"21","article-title":"Layer normalization","volume":"1050","author":"ba","year":"2016","journal-title":"Stat"},{"key":"ref26","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref43","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"key":"ref25","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc ICML"}],"event":{"name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Daegu, Korea","start":{"date-parts":[[2021,5,22]]},"end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9401028\/9401051\/09401485.pdf?arnumber=9401485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,25]],"date-time":"2022-12-25T16:17:10Z","timestamp":1671985030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9401485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iscas51556.2021.9401485","relation":{},"subject":[],"published":{"date-parts":[[2021,5]]}}}