{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T15:12:07Z","timestamp":1748358727072,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/taslp.2017.2756818","type":"journal-article","created":{"date-parts":[[2017,11,23]],"date-time":"2017-11-23T19:08:05Z","timestamp":1511464085000},"page":"2351-2361","source":"Crossref","is-referenced-by-count":3,"title":["Synthesis of Tongue Motion and Acoustics From Text Using a Multimodal Articulatory Database"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6415-5915","authenticated-orcid":false,"given":"Ingmar","family":"Steiner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0407-8318","authenticated-orcid":false,"given":"Sebastien","family":"Le Maguer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Hewer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.05.008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2215600"},{"key":"ref31","first-page":"207","article-title":"Mage—Reactive articulatory feature control of HMM-based parametric speech synthesis","author":"astrinaki","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2103058"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24726-7_16"},{"article-title":"Control of talking heads by acoustic-to-articulatory inversion for language learning and rehabilitation","year":"2011","author":"youssef","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.10.006"},{"key":"ref34","first-page":"665","article-title":"Evaluation of a system for concatenative articulatory visual speech synthesis","author":"engwall","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref28","first-page":"1569","article-title":"A real-time framework for visual feedback of articulatory data using statistical shape models","author":"james","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00132-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.2404622"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113558"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.413621"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.2002.0166"},{"key":"ref22","first-page":"157","article-title":"Analysis of tongue configuration in multi-speaker, multi-volume MRI data","author":"hoole","year":"0","journal-title":"Proc 5th Seminar Speech Prod"},{"key":"ref21","first-page":"395","article-title":"Three-dimensional linear modeling of tongue: Articulatory data and models","author":"badin","year":"0","journal-title":"Proc 7th Int Semin Speech Prod"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.1520538"},{"key":"ref23","first-page":"1588","article-title":"Predicting unseen articulations from multi-speaker articulatory models","author":"ananthakrishnan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1007\/978-3-540-70517-8_14","article-title":"An audiovisual talking head for augmented speech generation: Models and animations based on a real speaker's articulatory data","author":"badin","year":"2008","journal-title":"Articulated Motion and Deformable Objects"},{"key":"ref25","first-page":"1174","article-title":"Opti-Speech: A real-time, 3D visual feedback system for speech training","author":"katz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2281036"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1121\/1.3675459"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1250\/ast.36.467"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.21437\/Interspeech.2011-316","article-title":"Announcing the electromagnetic articulography (day 1) subset of the mngu0 articulatory corpus","author":"richmond","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-76","article-title":"An overview of Nitech HMM-based speech synthesis system for Blizzard Challenge 2005","author":"zen","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref13","article-title":"A multilinear tongue model derived from speech related MRI data of the human vocal tract","volume":"abs 1612 5005","author":"hewer","year":"2016","journal-title":"CoRR"},{"key":"ref14","first-page":"74","article-title":"Ultrax: An animated midsagittal vocal tract display for speech therapy","author":"richmond","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/8415_2012_126"},{"key":"ref16","first-page":"1","article-title":"Development of a 3D tongue motion visualization platform based on ultrasound image sequences","author":"xu","year":"0","journal-title":"Proc 18th Int Congr Phonetic Scences"},{"key":"ref17","first-page":"1","article-title":"Towards a 3D tongue model for parameterising ultrasound data","author":"wrench","year":"0","journal-title":"Proc 18th Int Congr Phonetic Scences"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3929-6"},{"key":"ref19","first-page":"901","article-title":"A 3D tongue model based on MRI data.","author":"engwall","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0093-934X(87)90058-7"},{"journal-title":"X-ray microbeam speech production database user's handbook","year":"1994","author":"westbury","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24276"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199235797.003.0020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2014796"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.4890284"},{"key":"ref49","first-page":"275","article-title":"Dynamic units of visual speech","author":"taylor","year":"0","journal-title":"Proc Eurograph \/ACM SIGGRAPH Symp Comput Animation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.06.006"},{"key":"ref46","first-page":"430","article-title":"Evaluation of prosodic contextual factors for HMM-based speech synthesis","author":"yokomizo","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"A biomechanical tongue model for speech production based on MRI live speaker data","year":"2011","author":"baker","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2012.03.002"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.4763549"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref44","first-page":"2194","article-title":"HMM-based text-to-articulatory-movement prediction and analysis of critical articulators","author":"ling","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref43","first-page":"137","article-title":"An adaptative algorithm for mel-cepstral analysis of speech","volume":"1","author":"fukada","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8114348\/08114352.pdf?arnumber=8114352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T05:35:29Z","timestamp":1659936929000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8114352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":51,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2756818","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}