{"id":"https://openalex.org/W2994459744","doi":"https://doi.org/10.1109/icawst.2019.8923588","title":"Acoustic-to-Articulatory Inversion of a Three-dimensional Theoretical Vocal Tract Model Using Deep Learning-based Model","display_name":"Acoustic-to-Articulatory Inversion of a Three-dimensional Theoretical Vocal Tract Model Using Deep Learning-based Model","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2994459744","doi":"https://doi.org/10.1109/icawst.2019.8923588","mag":"2994459744"},"language":"en","primary_location":{"id":"doi:10.1109/icawst.2019.8923588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icawst.2019.8923588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076531368","display_name":"Thanat Lapthawan","orcid":"https://orcid.org/0000-0002-9820-1980"},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Thanat Lapthawan","raw_affiliation_strings":["Department of Computer Engineering, King Mongkut\u2019s University of Technology Thonburi, Bangkok, Thailand","Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Mongkut\u2019s University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]},{"raw_affiliation_string":"Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003455071","display_name":"Santitham Prom\u2013on","orcid":"https://orcid.org/0000-0002-0869-089X"},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Santitham Prom-on","raw_affiliation_strings":["Department of Computer Engineering, King Mongkut\u2019s University of Technology Thonburi, Bangkok, Thailand","Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Mongkut\u2019s University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]},{"raw_affiliation_string":"Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076531368"],"corresponding_institution_ids":["https://openalex.org/I60837268"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58999744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"521","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.9199463129043579},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.7404024600982666},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6593440771102905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6208748817443848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5710883736610413},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5496741533279419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5348414778709412},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5052180886268616},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48578885197639465},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.43331044912338257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38185036182403564},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.316433846950531},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1151244044303894}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.9199463129043579},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.7404024600982666},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6593440771102905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6208748817443848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5710883736610413},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5496741533279419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5348414778709412},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5052180886268616},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48578885197639465},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.43331044912338257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38185036182403564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.316433846950531},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1151244044303894},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icawst.2019.8923588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icawst.2019.8923588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W201148316","https://openalex.org/W423487555","https://openalex.org/W1499220978","https://openalex.org/W1499800345","https://openalex.org/W1531956331","https://openalex.org/W1595178389","https://openalex.org/W1665214252","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2111701360","https://openalex.org/W2116128780","https://openalex.org/W2123778414","https://openalex.org/W2131774270","https://openalex.org/W2191779130","https://openalex.org/W2596135543","https://openalex.org/W2746549158","https://openalex.org/W2785523195","https://openalex.org/W2787248829","https://openalex.org/W2888898948","https://openalex.org/W2919115771","https://openalex.org/W2943899479","https://openalex.org/W2949117887","https://openalex.org/W2979074722","https://openalex.org/W6608180490","https://openalex.org/W6614726025","https://openalex.org/W6629654537","https://openalex.org/W6677479525","https://openalex.org/W6735255722"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2131046383","https://openalex.org/W2050311283"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"acoustic-to-articulatory":[4],"mapping":[5],"of":[6,53,56,123,130,137,143,153,194],"a":[7,46,151,154,191,195],"three-dimensional":[8,47,192],"theoretical":[9,48],"vocal":[10,37,70,196],"tract":[11,38,71,197],"model":[12,184],"using":[13,91,111],"deep":[14,18,104,182],"learning":[15],"methods.":[16],"Prominent":[17],"learning-based":[19,183],"network":[20,107],"structures":[21],"are":[22],"explored":[23],"and":[24,35,64,84,96,125,135,160,174],"evaluated":[25,90],"for":[26,118,132,145],"their":[27],"suitability":[28],"in":[29,51,77,190],"capturing":[30],"the":[31,54,78,92,115,161,181],"relationship":[32],"between":[33,150,172],"acoustic":[34],"articulatory-oriented":[36],"parameters.":[39,72,176],"The":[40,73,103,148,177],"dataset":[41,79],"was":[42],"synthesized":[43,163],"from":[44,156],"VocalTractLab,":[45],"articulatory":[49,65,158,188],"synthesizer,":[50],"forms":[52],"pairs":[55],"acoustic,":[57],"represented":[58,67],"by":[59,68],"Mel-frequency":[60],"cepstral":[61],"coefficients":[62],"(MFCCs),":[63],"signals,":[66],"23":[69],"sentence":[74],"structure":[75],"used":[76],"generation":[80],"were":[81,89],"both":[82,119],"monosyllabic":[83,133],"disyllabic":[85,146],"vowel":[86],"articulations.":[87],"Models":[88],"root-mean-square":[93],"error":[94],"(RMSE)":[95],"R-squared":[97],"(R":[98],"<sup":[99,127,140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100,128,141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[101,129,142],").":[102],"artificial":[105],"neural":[106],"architecture":[108],"(DNN),":[109],"regulating":[110],"batch":[112],"normalization,":[113],"achieves":[114],"best":[116],"performance":[117],"inversion":[120],"tasks,":[121],"RMSE":[122,136],"0.015":[124],"R":[126,139],"0.970":[131],"vowels":[134],"0.015and":[138],"0.975":[144],"vowels.":[147],"comparison,":[149],"formant":[152],"sound":[155],"inverted":[157],"parameters":[159,189],"original":[162,173],"sound,":[164],"demonstrates":[165],"that":[166,180],"there":[167],"is":[168,185],"no":[169],"statistically":[170],"different":[171],"estimated":[175,187],"results":[178],"indicate":[179],"effectively":[186],"space":[193],"model.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}