{"id":"https://openalex.org/W2940114504","doi":"https://doi.org/10.1109/ijcnn.2019.8851769","title":"DNN-based Acoustic-to-Articulatory Inversion using Ultrasound Tongue Imaging","display_name":"DNN-based Acoustic-to-Articulatory Inversion using Ultrasound Tongue Imaging","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2940114504","doi":"https://doi.org/10.1109/ijcnn.2019.8851769","mag":"2940114504"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.06083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027804141","display_name":"Dagoberto Porras","orcid":null},"institutions":[{"id":"https://openalex.org/I115684694","display_name":"Industrial University of Santander","ror":"https://ror.org/00xc1d948","country_code":"CO","type":"education","lineage":["https://openalex.org/I115684694"]}],"countries":["CO"],"is_corresponding":true,"raw_author_name":"Dagoberto Porras","raw_affiliation_strings":["Escuela de Ingenier\u00edas El\u00e9ctrica, Electr\u00f3nica y Telecomunicaciones, Universidad Industrial de Santander Bucaramanga, Santander, Colombia"],"affiliations":[{"raw_affiliation_string":"Escuela de Ingenier\u00edas El\u00e9ctrica, Electr\u00f3nica y Telecomunicaciones, Universidad Industrial de Santander Bucaramanga, Santander, Colombia","institution_ids":["https://openalex.org/I115684694"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029149936","display_name":"Alexander Sep\u00falveda","orcid":"https://orcid.org/0000-0002-9643-5193"},"institutions":[{"id":"https://openalex.org/I115684694","display_name":"Industrial University of Santander","ror":"https://ror.org/00xc1d948","country_code":"CO","type":"education","lineage":["https://openalex.org/I115684694"]}],"countries":["CO"],"is_corresponding":false,"raw_author_name":"Alexander Sepulveda-Sepulveda","raw_affiliation_strings":["Escuela de Ingenier\u00edas El\u00e9ctrica, Electr\u00f3nica y Telecomunicaciones, Universidad Industrial de Santander Bucaramanga, Santander, Colombia"],"affiliations":[{"raw_affiliation_string":"Escuela de Ingenier\u00edas El\u00e9ctrica, Electr\u00f3nica y Telecomunicaciones, Universidad Industrial de Santander Bucaramanga, Santander, Colombia","institution_ids":["https://openalex.org/I115684694"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tamas Gabor Csapo","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics","Dept. of Telecommunications and Media Informatics, Budapest University of Technology and Economics,"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Dept. of Telecommunications and Media Informatics, Budapest University of Technology and Economics,","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027804141"],"corresponding_institution_ids":["https://openalex.org/I115684694"],"apc_list":null,"apc_paid":null,"fwci":0.1676,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.42030754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9883999824523926,"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/T11309","display_name":"Music and Audio Processing","score":0.9631999731063843,"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/computer-science","display_name":"Computer science","score":0.7319621443748474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.584470808506012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.492364764213562},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.4759133458137512},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.4280986785888672},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37735894322395325},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3412958085536957},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28885191679000854},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.2255258560180664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319621443748474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.584470808506012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.492364764213562},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.4759133458137512},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.4280986785888672},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37735894322395325},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3412958085536957},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28885191679000854},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.2255258560180664},{"id":"https://openalex.org/C204723758","wikidata":"https://www.wikidata.org/wiki/Q3882459","display_name":"Acoustic wave","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.06083","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.06083","pdf_url":"https://arxiv.org/pdf/1904.06083","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2940114504","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.06083","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.06083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.06083","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.06083","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.06083","pdf_url":"https://arxiv.org/pdf/1904.06083","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311358","display_name":"Budapesti M\u0171szaki \u00e9s Gazdas\u00e1gtudom\u00e1nyi Egyetem","ror":"https://ror.org/02w42ss30"},{"id":"https://openalex.org/F4320325610","display_name":"Universidad Industrial de Santander","ror":"https://ror.org/00xc1d948"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2940114504.pdf","grobid_xml":"https://content.openalex.org/works/W2940114504.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W435022884","https://openalex.org/W1531956331","https://openalex.org/W1663785051","https://openalex.org/W1973016470","https://openalex.org/W1982854652","https://openalex.org/W1993882792","https://openalex.org/W1995440941","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2039640471","https://openalex.org/W2043003570","https://openalex.org/W2052382192","https://openalex.org/W2069618035","https://openalex.org/W2101802380","https://openalex.org/W2109272898","https://openalex.org/W2129160496","https://openalex.org/W2133665775","https://openalex.org/W2135707066","https://openalex.org/W2143929858","https://openalex.org/W2145442746","https://openalex.org/W2150734399","https://openalex.org/W2160815625","https://openalex.org/W2191779130","https://openalex.org/W2294901616","https://openalex.org/W2340712740","https://openalex.org/W2398783778","https://openalex.org/W2406959878","https://openalex.org/W2419247625","https://openalex.org/W2508425411","https://openalex.org/W2515755543","https://openalex.org/W2554625447","https://openalex.org/W2603597171","https://openalex.org/W2623570296","https://openalex.org/W2746109435","https://openalex.org/W2762685704","https://openalex.org/W2769402512","https://openalex.org/W2769531941","https://openalex.org/W2770785043","https://openalex.org/W2888898948","https://openalex.org/W2889413431","https://openalex.org/W2889853672","https://openalex.org/W2990782011","https://openalex.org/W6601427873","https://openalex.org/W6602447114","https://openalex.org/W6631452893","https://openalex.org/W6634534149","https://openalex.org/W6711834147","https://openalex.org/W6712170184","https://openalex.org/W6712967625","https://openalex.org/W6737144389","https://openalex.org/W6754356477","https://openalex.org/W6754885506","https://openalex.org/W7054043781"],"related_works":["https://openalex.org/W2979074722","https://openalex.org/W2146499996","https://openalex.org/W2005689542","https://openalex.org/W1986174057","https://openalex.org/W3193558558","https://openalex.org/W1987446027","https://openalex.org/W2603958585","https://openalex.org/W2294901616","https://openalex.org/W2940009604","https://openalex.org/W2744379673","https://openalex.org/W3157356148","https://openalex.org/W1559678887","https://openalex.org/W2972363853","https://openalex.org/W2159731626","https://openalex.org/W2745751587","https://openalex.org/W60893253","https://openalex.org/W2787642068","https://openalex.org/W3096158177","https://openalex.org/W1989674786","https://openalex.org/W3164409797"],"abstract_inverted_index":{"Speech":[0],"sounds":[1],"are":[2,13,61,74],"produced":[3],"as":[4,35,125,206,222],"the":[5,9,19,25,53,57,81,134,138,143,153,176,182,209,219,223,241,248,252],"coordinated":[6],"movement":[7],"of":[8,21,72,94,195,202,232],"speaking":[10],"organs.":[11],"There":[12,60],"several":[14,45,62],"available":[15],"methods":[16],"to":[17,51,66,85,114,118,132,218,240],"model":[18],"relation":[20],"articulatory":[22,54,82,135],"movements":[23],"and":[24,106,141,164,226],"resulting":[26],"speech":[27,124],"signal.":[28,59],"The":[29],"reverse":[30],"problem":[31],"is":[32,91,113,175],"often":[33],"called":[34],"acoustic-to-articulatory":[36],"inversion":[37,264],"(AAI).":[38],"In":[39,244],"this":[40,68,263],"paper":[41],"we":[42,98,157],"have":[43],"implemented":[44],"different":[46,188],"Deep":[47],"Neural":[48],"Networks":[49],"(DNNs)":[50],"estimate":[52],"information":[55],"from":[56],"acoustic":[58],"previous":[63],"works":[64],"related":[65],"performing":[67],"task,":[69],"but":[70,213],"most":[71,177],"them":[73],"using":[75,123],"ElectroMagnetic":[76],"Articulography":[77],"(EMA)":[78],"for":[79,152,262],"tracking":[80],"movement.":[83],"Compared":[84],"EMA,":[86],"Ultrasound":[87],"Tongue":[88],"Imaging":[89],"(UTI)":[90],"a":[92,116,227,245],"technique":[93],"higher":[95],"cost-benefit":[96],"if":[97],"take":[99],"into":[100],"account":[101],"equipment":[102],"cost,":[103],"portability,":[104],"safety":[105],"visualized":[107],"structures.":[108],"Seeing":[109],"that,":[110],"our":[111],"goal":[112],"train":[115],"DNN":[117,193,212,230],"obtain":[119],"UT":[120,155],"images,":[121,156],"when":[122],"input.":[126],"We":[127,185],"also":[128],"test":[129],"two":[130,256],"approaches":[131],"represent":[133],"information:":[136],"1)":[137],"EigenTongue":[139,220,242],"space":[140,221],"2)":[142],"raw":[144],"ultrasound":[145,215],"image.":[146],"As":[147],"an":[148,203],"objective":[149],"quality":[150],"measure":[151,180],"reconstructed":[154],"use":[158],"MSE,":[159],"Structural":[160],"Similarity":[161],"Index":[162],"(SSIM)":[163],"Complex-":[165],"Wavelet":[166],"SSIM":[167],"(CW-SSIM).":[168],"Our":[169],"experimental":[170],"results":[171],"show":[172],"that":[173,251],"CW-SSIM":[174],"useful":[178],"error":[179],"in":[181],"UTI":[183,204,237],"context.":[184],"tested":[186],"three":[187],"system":[189],"configurations:":[190],"a)":[191],"simple":[192,211],"composed":[194,231],"2":[196],"hidden":[197,234,257],"layers":[198,235,258],"with":[199,214,236,255],"64x64":[200],"pixels":[201],"file":[205],"target;":[207,224],"b)":[208],"same":[210],"images":[216],"projected":[217,239],"c)":[225],"more":[228,260],"complex":[229],"5":[233],"files":[238],"space.":[243],"subjective":[246],"experiment":[247],"subjects":[249],"found":[250],"neural":[253],"networks":[254],"were":[259],"suitable":[261],"task.":[265]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}