{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:29:37Z","timestamp":1777984177821,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","award":["RPG-2019-241"],"award-info":[{"award-number":["RPG-2019-241"]}],"id":[{"id":"10.13039\/501100000275","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":[[2023]]},"DOI":"10.1109\/taslp.2023.3264454","type":"journal-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T13:45:53Z","timestamp":1680702353000},"page":"1734-1744","source":"Crossref","is-referenced-by-count":6,"title":["Artificial Vocal Learning Guided by Phoneme Recognition and Visual Information"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8518-8142","authenticated-orcid":false,"given":"Paul Konstantin","family":"Krug","sequence":"first","affiliation":[{"name":"Institute of Acoustics and Speech Communication, Technische Universität, Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0167-8123","authenticated-orcid":false,"given":"Peter","family":"Birkholz","sequence":"additional","affiliation":[{"name":"Institute of Acoustics and Speech Communication, Technische Universität, Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Branislav","family":"Gerazov","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Information Technologies, Ss. Cyril and Methodius University, Skopje, North Macedonia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7324-2751","authenticated-orcid":false,"given":"Daniel Rudolph","family":"van Niekerk","sequence":"additional","affiliation":[{"name":"Department of Speech, Hearing and Phonetic Sciences, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4331-6676","authenticated-orcid":false,"given":"Anqi","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8541-2658","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Speech, Hearing and Phonetic Sciences, University College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(97)00025-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"ref12","first-page":"159","article-title":"Training a vocal tract synthesiser to imitate speech using distal supervised learning","volume":"2","author":"howard","year":"0","journal-title":"Proc 10th Int Conf Speech Comput"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.12.022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.08.002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2006.10.002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107224"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2016.01.008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/4-431-31381-8_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(92)90036-T"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"},{"key":"ref10","first-page":"52","article-title":"Articulatory copy synthesis using long-short term memory networks","author":"gao","year":"0","journal-title":"Proc Studientexte zur Sprachkommunikation Elektronische Sprachsignalverarbeitung"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10874"},{"key":"ref2","author":"pereira","year":"1999","journal-title":"Language development and social interactionin blind children"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2012.11.002"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/01690960903498424"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.59"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.010"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2016.7846793"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/10.0005876"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-2037-8_6"},{"key":"ref26","first-page":"51","article-title":"Efficient exploration of articulatory dimensions","author":"krug","year":"0","journal-title":"Proc Studientexte zur Sprachkommunikation Elektronische Sprachsignalverarbeitung"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2545"},{"key":"ref20","first-page":"304","article-title":"Modelling vowel acquisition using the Birkholz synthesizer","author":"howard","year":"0","journal-title":"Proc Studientexte zur Sprachkommunikation Elektronische Sprachsignalverarbeitung"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3041179"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-021-00704-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCSW.2011.20"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.3037222"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00063-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2091632"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2014.6982981"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0060603"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1334"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.3158930"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-8202-7_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2015.7346142"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.4818740"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00045"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10093052.pdf?arnumber=10093052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T13:41:28Z","timestamp":1685367688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10093052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3264454","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.20502114","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.20502114.v1","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}