{"id":"https://openalex.org/W2569953749","doi":"https://doi.org/10.1109/taslp.2017.2756818","title":"Synthesis of Tongue Motion and Acoustics From Text Using a Multimodal Articulatory Database","display_name":"Synthesis of Tongue Motion and Acoustics From Text Using a Multimodal Articulatory Database","publication_year":2017,"publication_date":"2017-11-23","ids":{"openalex":"https://openalex.org/W2569953749","doi":"https://doi.org/10.1109/taslp.2017.2756818","mag":"2569953749"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2756818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2756818","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.09352","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ingmar Steiner","orcid":"https://orcid.org/0000-0001-6415-5915"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ingmar Steiner","raw_affiliation_strings":["Cluster of Excellence \u201cMultimodal Computing and Interaction,\u201d, Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6415-5915","affiliations":[{"raw_affiliation_string":"Cluster of Excellence \u201cMultimodal Computing and Interaction,\u201d, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sebastien Le Maguer","orcid":"https://orcid.org/0000-0003-0407-8318"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastien Le Maguer","raw_affiliation_strings":["Cluster of Excellence \u201cMultimodal Computing and Interaction,\u201d, Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0407-8318","affiliations":[{"raw_affiliation_string":"Cluster of Excellence \u201cMultimodal Computing and Interaction,\u201d, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alexander Hewer","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Hewer","raw_affiliation_strings":["Cluster of Excellence \u201cMultimodal Computing and Interaction,\u201d, Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cluster of Excellence \u201cMultimodal Computing and Interaction,\u201d, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.00614251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"25","issue":"12","first_page":"2351","last_page":"2361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.4650000035762787,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.4650000035762787,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.22709999978542328,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.0364999994635582,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.6055999994277954},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5910000205039978},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5705999732017517},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4544999897480011},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4140999913215637},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.38370001316070557},{"id":"https://openalex.org/keywords/articulatory-phonetics","display_name":"Articulatory phonetics","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185999751091003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.652400016784668},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.6055999994277954},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4819999933242798},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.38370001316070557},{"id":"https://openalex.org/C30896174","wikidata":"https://www.wikidata.org/wiki/Q1200775","display_name":"Articulatory phonetics","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C194226119","wikidata":"https://www.wikidata.org/wiki/Q161779","display_name":"Spatial reference system","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2017.2756818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2756818","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1612.09352","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.09352","pdf_url":"https://arxiv.org/pdf/1612.09352","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1612.09352","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.09352","pdf_url":"https://arxiv.org/pdf/1612.09352","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W634209149","https://openalex.org/W1563645159","https://openalex.org/W1607802755","https://openalex.org/W1963826206","https://openalex.org/W1968245896","https://openalex.org/W1985659269","https://openalex.org/W1990369770","https://openalex.org/W1995440941","https://openalex.org/W2006994810","https://openalex.org/W2013317861","https://openalex.org/W2032693983","https://openalex.org/W2037042749","https://openalex.org/W2049686551","https://openalex.org/W2051434435","https://openalex.org/W2052382192","https://openalex.org/W2056387890","https://openalex.org/W2065086021","https://openalex.org/W2066381494","https://openalex.org/W2067517374","https://openalex.org/W2116082100","https://openalex.org/W2129142580","https://openalex.org/W2131770202","https://openalex.org/W2132733106","https://openalex.org/W2135707066","https://openalex.org/W2154920538","https://openalex.org/W2184487591","https://openalex.org/W2198017374","https://openalex.org/W2231075402","https://openalex.org/W2260035229","https://openalex.org/W2523920055","https://openalex.org/W2525385801","https://openalex.org/W4232572160","https://openalex.org/W4392282756","https://openalex.org/W6607924995","https://openalex.org/W6607963373","https://openalex.org/W6628106731","https://openalex.org/W6631607239","https://openalex.org/W6635255037","https://openalex.org/W6650605322","https://openalex.org/W6697039285","https://openalex.org/W6712007117","https://openalex.org/W6712245969","https://openalex.org/W6713451393","https://openalex.org/W6732717329","https://openalex.org/W6734509241","https://openalex.org/W6785585278","https://openalex.org/W6844911191"],"related_works":[],"abstract_inverted_index":{"We":[0,48],"present":[1],"an":[2,31,89],"end-to-end":[3],"text-to-speech":[4],"(TTS)":[5],"synthesis":[6,40],"system":[7,41],"that":[8],"generates":[9],"audio":[10],"and":[11,34,81],"synchronized":[12],"tongue":[13,28,45],"motion":[14],"directly":[15,42],"from":[16],"text.":[17],"This":[18],"is":[19],"achieved":[20],"by":[21,55],"adapting":[22],"a":[23,36,71],"three-dimensional":[24],"model":[25,46,51],"of":[26,60,76],"the":[27,44,50,57,65,97],"surface":[29],"to":[30,87,92],"articulatory":[32,62,90],"dataset":[33],"training":[35],"statistical":[37],"parametric":[38],"speech":[39],"on":[43],"parameters.":[47],"evaluate":[49],"at":[52],"every":[53],"step":[54],"comparing":[56],"spatial":[58],"coordinates":[59],"predicted":[61],"movements":[63],"against":[64],"reference":[66],"data.":[67,101],"The":[68],"results":[69],"indicate":[70],"global":[72],"mean":[73],"Euclidean":[74],"distance":[75],"less":[77],"than":[78],"2.8":[79],"mm,":[80],"our":[82],"approach":[83],"can":[84],"be":[85],"adapted":[86],"add":[88],"modality":[91],"conventional":[93],"TTS":[94],"applications":[95],"without":[96],"need":[98],"for":[99],"extra":[100]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2017-01-13T00:00:00"}