{"id":"https://openalex.org/W4416936616","doi":"https://doi.org/10.1186/s13636-025-00438-x","title":"Multilingual speech-to-vocal tract visualization using deep learning for pronunciation training","display_name":"Multilingual speech-to-vocal tract visualization using deep learning for pronunciation training","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416936616","doi":"https://doi.org/10.1186/s13636-025-00438-x"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00438-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00438-x","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13636-025-00438-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028921525","display_name":"Rodrigo Picinini M\u00e9xas","orcid":"https://orcid.org/0000-0002-2627-8743"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Rodrigo Picinini M\u00e9xas","raw_affiliation_strings":["Computer Science and Engineering Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109698956","display_name":"Yunji Chu","orcid":"https://orcid.org/0009-0003-8348-1312"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunji Chu","raw_affiliation_strings":["Artificial Intelligence Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046573028","display_name":"Unsang Park","orcid":"https://orcid.org/0000-0001-5539-9520"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Unsang Park","raw_affiliation_strings":["Artificial Intelligence Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea","Computer Science and Engineering Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5539-9520","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Computer Science and Engineering Department, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul, 04107, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046573028"],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":1.1078,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83068467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2026","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.47929999232292175,"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":0.47929999232292175,"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/T10863","display_name":"Voice and Speech Disorders","score":0.12700000405311584,"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"}},{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.10419999808073044,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.732200026512146},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6568999886512756},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6281999945640564},{"id":"https://openalex.org/keywords/helpfulness","display_name":"Helpfulness","score":0.48570001125335693},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44359999895095825},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.43470001220703125},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38029998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9172999858856201},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.732200026512146},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5040000081062317},{"id":"https://openalex.org/C2781265381","wikidata":"https://www.wikidata.org/wiki/Q5710255","display_name":"Helpfulness","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4551999866962433},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00438-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00438-x","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:caddf4e7b2d7442dbd024e571d0db9df","is_oa":true,"landing_page_url":"https://doaj.org/article/caddf4e7b2d7442dbd024e571d0db9df","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2026, Iss 1, Pp 1-15 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00438-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00438-x","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1965378753","https://openalex.org/W2066381494","https://openalex.org/W2113905093","https://openalex.org/W2954762032","https://openalex.org/W3081492798","https://openalex.org/W3130860000","https://openalex.org/W3154411171","https://openalex.org/W3209059054","https://openalex.org/W4205788843","https://openalex.org/W4224245459","https://openalex.org/W4225152073","https://openalex.org/W4304142059","https://openalex.org/W4312617489","https://openalex.org/W4319983190","https://openalex.org/W4372340876","https://openalex.org/W4372348980","https://openalex.org/W4385626247","https://openalex.org/W4385823264","https://openalex.org/W4386065999","https://openalex.org/W4386076250","https://openalex.org/W4387421789","https://openalex.org/W4387823102","https://openalex.org/W4388672923","https://openalex.org/W4390874429","https://openalex.org/W4396671862","https://openalex.org/W4409353060"],"related_works":[],"abstract_inverted_index":{"Visualizing":[0],"the":[1,23,39,98,130,143,161,172,199,204,210],"vocal":[2,59],"tract":[3,60],"during":[4],"speech":[5,43,56,94],"remains":[6],"a":[7,51,70,103,133,139,193],"challenging":[8],"task,":[9],"even":[10],"with":[11,31,84],"recent":[12],"advancements":[13],"in":[14,113,188],"open-source":[15],"algorithms":[16],"and":[17,82,122,137,157,164,180,183,207],"datasets.":[18],"A":[19],"key":[20],"limitation":[21],"is":[22,76],"lack":[24],"of":[25,41,93,174,198,209],"multimodal":[26],"resources":[27],"that":[28,54,106],"integrate":[29],"audio":[30,108,125],"internal":[32],"articulatory":[33,110,145],"structures,":[34],"which":[35],"poses":[36],"challenges":[37],"to":[38,64,109,141,202,213],"development":[40],"effective":[42],"visualization":[44,92],"methods.":[45],"In":[46],"this":[47],"work,":[48],"we":[49,101,128,148],"propose":[50],"novel":[52],"algorithm":[53],"translates":[55],"into":[57],"dynamic":[58],"movements,":[61],"enabling":[62],"users":[63],"visually":[65],"compare":[66],"their":[67],"articulation":[68],"against":[69],"correctly":[71],"pronounced":[72],"reference.":[73],"This":[74],"approach":[75,176],"particularly":[77],"beneficial":[78],"for":[79,124,152,168],"language":[80],"learners":[81],"individuals":[83],"congenital":[85],"deafness,":[86],"as":[87,119,132],"it":[88],"provides":[89],"an":[90,215],"intuitive":[91],"production.":[95],"To":[96],"address":[97],"dataset":[99],"gap,":[100],"construct":[102],"new":[104],"corpus":[105],"maps":[107],"parameters":[111],"used":[112],"VocalTractLab.":[114],"Leveraging":[115],"pretrained":[116],"models":[117,167],"such":[118],"Wav2Vec":[120],"2.0":[121],"HuBERT":[123],"feature":[126],"extraction,":[127],"frame":[129],"task":[131],"sequence-to-sequence":[134],"learning":[135],"problem":[136],"employ":[138],"Bi-GRU":[140],"predict":[142],"corresponding":[144],"parameters.":[146],"Furthermore,":[147],"develop":[149],"language-specific":[150],"datasets":[151],"General":[153],"American":[154],"English,":[155],"Korean,":[156],"Brazilian":[158],"Portuguese":[159],"using":[160],"same":[162],"pipeline,":[163],"train":[165],"dedicated":[166],"each.":[169],"We":[170],"validate":[171],"effectiveness":[173],"our":[175],"through":[177,192],"both":[178],"qualitative":[179],"quantitative":[181],"evaluations":[182],"assess":[184],"its":[185],"practical":[186],"utility":[187],"pronunciation":[189,217],"correction":[190,218],"tasks":[191],"user":[194],"survey.":[195],"The":[196],"goal":[197],"survey":[200],"was":[201],"evaluate":[203],"perceived":[205],"helpfulness":[206],"usability":[208],"visualizations,":[211],"not":[212],"implement":[214],"iterative":[216],"process.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-03T00:00:00"}