{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:23Z","timestamp":1740172463919,"version":"3.37.3"},"reference-count":58,"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"}],"funder":[{"DOI":"10.13039\/501100001695","name":"JST","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009023","name":"PRESTO","doi-asserted-by":"crossref","award":["JPMJPR1657"],"award-info":[{"award-number":["JPMJPR1657"]}],"id":[{"id":"10.13039\/501100009023","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000646","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["17H01763"],"award-info":[{"award-number":["17H01763"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"JSPS","doi-asserted-by":"publisher","award":["16J10726"],"award-info":[{"award-number":["16J10726"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"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.2017.2753583","type":"journal-article","created":{"date-parts":[[2017,11,23]],"date-time":"2017-11-23T19:08:05Z","timestamp":1511464085000},"page":"2337-2350","source":"Crossref","is-referenced-by-count":3,"title":["Articulatory Controllable Speech Modification Based on Statistical Inversion and Production Mappings"],"prefix":"10.1109","volume":"25","author":[{"given":"Patrick Lumban","family":"Tobing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"79","DOI":"10.21248\/zaspil.40.2005.259","article-title":"A visual articulatory model and its application to therapy of speech disorders: A pilot study","volume":"40","author":"kr\u00f6ger","year":"2005","journal-title":"Speech Production Perception Exp Anal Models ZAS Papers Linguistics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2215600"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.02.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.1715112"},{"key":"ref31","first-page":"433","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 Int Conf Spoken Lang Process"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.21437\/Interspeech.2004-410","article-title":"Acoustic-to-articulatory inversion mapping with Gaussian mixture model","author":"toda","year":"2004","journal-title":"Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.001"},{"key":"ref35","first-page":"31","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 of 5th ISCA Tutorial and Research Workshop on Speech Synthesis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659965"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.822636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77347-4_23"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.21437\/Interspeech.2009-640","article-title":"Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models","author":"youssef","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0093-934X(87)90058-7"},{"key":"ref22","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":"ref21","first-page":"305","article-title":"A multichannel articulatory database and its application for automatic speech recognition","author":"wrench","year":"2000","journal-title":"Proc 5th Seminar Speech Prod"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.416001"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"837","DOI":"10.21437\/Interspeech.2011-308","article-title":"A multimodal real-time MRI articulatory corpus for speech research","author":"narayanan","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(03)00005-6"},{"key":"ref25","first-page":"2251","article-title":"Determination of articulatory positions from speech acoustics by applying dynamic articulatory constraints","author":"suzuki","year":"1998","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2522655"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref58","first-page":"2446","article-title":"Eigenvoice conversion based on Gaussian mixture model","author":"toda","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947385"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1399"},{"key":"ref55","first-page":"270","article-title":"Analysis and synthesis of hypo- and hyperarticulated speech","author":"picart","year":"2010","journal-title":"Proc 4th ISCA Tutorial and Research Workshop on Speech Synthesis"},{"key":"ref54","first-page":"2781","article-title":"Fixed point analysis of frequency to instantaneous frequency mapping for accurate estimation of F0 and periodicity","author":"kawahara","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref52","first-page":"2754","article-title":"Statistical singing voice conversion based on direct waveform modification with global variance","author":"kobayashi","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00020-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.2404622"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"2639","DOI":"10.21437\/Interspeech.2008-654","article-title":"Two- and three-dimensional visual articulatory models for pronunciation training and for treatment of speech disorders","author":"kr\u00f6ger","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"755","article-title":"MOTHER: A new generation of talking heads providing a flexible articulatory control for video-realistic speech animation","author":"rev\u00e9ret","year":"2000","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70517-8_14"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/1.1910470"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163242"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.2003527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-2037-8_6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.1913427"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.381848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.1989.177049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165240"},{"key":"ref6","first-page":"231","article-title":"Speech coding based on physiological models of speech production","author":"schroeter","year":"1992","journal-title":"Advances in Speech Signal Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.260356"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2202","DOI":"10.21437\/Interspeech.2012-587","article-title":"Modeling a noisy-channel for voice conversion using articulatory features","author":"bollepali","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224376"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref9","first-page":"145","article-title":"Continuous speech recognition using articulatory data","author":"wrench","year":"2000","journal-title":"Proc Int Conf Spoken Lang Process"},{"year":"1999","author":"wrench","key":"ref46"},{"key":"ref45","first-page":"3350","article-title":"Articulatory controllable speech modification based on Gaussian mixture models with direct waveform modification using spectrum differential","author":"tobing","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.21437\/Interspeech.2010-567","article-title":"Can tongue be recovered from face? The answer of data-driven statistical models","author":"youssef","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12397-9_29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-3933-6_9"},{"key":"ref44","first-page":"2514","article-title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","author":"kobayashi","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref43","first-page":"2298","article-title":"Articulatory controllable speech modification based on statistical feature mapping with Gaussian mixture models","author":"tobing","year":"2014","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8114348\/08114384.pdf?arnumber=8114384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T05:35:43Z","timestamp":1659936943000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8114384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":58,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2753583","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}