{"id":"https://openalex.org/W6929326747","doi":"https://doi.org/10.48550/arxiv.2504.13308","title":"Acoustic to Articulatory Inversion of Speech; Data Driven Approaches, Challenges, Applications, and Future Scope","display_name":"Acoustic to Articulatory Inversion of Speech; Data Driven Approaches, Challenges, Applications, and Future Scope","publication_year":2025,"publication_date":"2025-04-17","ids":{"openalex":"https://openalex.org/W6929326747","doi":"https://doi.org/10.48550/arxiv.2504.13308"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.13308","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.13308","pdf_url":"https://arxiv.org/pdf/2504.13308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.13308","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006186008","display_name":"Leena G Pillai","orcid":"https://orcid.org/0000-0003-1692-7647","observed_orcids":["https://orcid.org/0000-0003-1692-7647"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pillai, Leena G","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054432484","display_name":"D. Muhammad Noorul Mubarak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mubarak, D. Muhammad Noorul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.70169997215271,"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":0.70169997215271,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.24629999697208405,"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/T10860","display_name":"Speech and Audio Processing","score":0.03819999843835831,"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/acoustic-to-articulatory-inversion","display_name":"acoustic-to-articulatory inversion","score":0.9829999804496765},{"id":"https://openalex.org/keywords/articulatory-synthesis","display_name":"articulatory speech synthesis","score":0.625},{"id":"https://openalex.org/keywords/electromagnetic-articulography","display_name":"electromagnetic articulography","score":0.7900000214576721},{"id":"https://openalex.org/keywords/electropalatography","display_name":"electropalatography","score":0.9900000095367432},{"id":"https://openalex.org/keywords/electroglottography","display_name":"electroglottography","score":0.9380000233650208},{"id":"https://openalex.org/keywords/ultrasonography","display_name":"ultrasonography","score":0.5490000247955322},{"id":"https://openalex.org/keywords/real-time-mri","display_name":"real-time MRI","score":0.7179999947547913},{"id":"https://openalex.org/keywords/speech-therapy","display_name":"speech therapy","score":0.9340000152587891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6510000228881836}],"concepts":[{"id":"https://openalex.org/C144251240","wikidata":"https://www.wikidata.org/wiki/Q7068229","display_name":"Nucleofection","level":4,"score":0.38609999418258667},{"id":"https://openalex.org/C2777158700","wikidata":"https://www.wikidata.org/wiki/Q1419356","display_name":"Hyporeflexia","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C2777054765","wikidata":"https://www.wikidata.org/wiki/Q6402731","display_name":"Dysgeusia","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C516976414","wikidata":"https://www.wikidata.org/wiki/Q1606582","display_name":"Nasalization","level":3,"score":0.23579999804496765},{"id":"https://openalex.org/C81746177","wikidata":"https://www.wikidata.org/wiki/Q4346098","display_name":"Windage","level":2,"score":0.2345000058412552},{"id":"https://openalex.org/C104545631","wikidata":"https://www.wikidata.org/wiki/Q464858","display_name":"Demotion","level":3,"score":0.23160000145435333},{"id":"https://openalex.org/C2781032047","wikidata":"https://www.wikidata.org/wiki/Q938793","display_name":"Articular cartilage damage","level":5,"score":0.22630000114440918},{"id":"https://openalex.org/C2992336715","wikidata":"https://www.wikidata.org/wiki/Q63431143","display_name":"Gestational period","level":4,"score":0.22519999742507935},{"id":"https://openalex.org/C133074676","wikidata":"https://www.wikidata.org/wiki/Q428729","display_name":"Fusible alloy","level":2,"score":0.21950000524520874},{"id":"https://openalex.org/C2778283623","wikidata":"https://www.wikidata.org/wiki/Q18032200","display_name":"TSG101","level":5,"score":0.21870000660419464}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.13308","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.13308","pdf_url":"https://arxiv.org/pdf/2504.13308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.13308","doi":"https://doi.org/10.48550/arxiv.2504.13308","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.13308","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.13308","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.13308","pdf_url":"https://arxiv.org/pdf/2504.13308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8137351870536804,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,18],"review":[1,19],"is":[2,132,140],"focused":[3],"on":[4,124],"the":[5,22,27,50,65,120,137,168],"data-driven":[6],"approaches":[7],"applied":[8],"in":[9,26],"different":[10],"applications":[11],"of":[12,16,38,49,167,181],"Acoustic-to-Articulatory":[13],"Inversion":[14],"(AAI)":[15],"speech.":[17],"paper":[20],"considered":[21,154],"relevant":[23],"works":[24,114,121],"published":[25],"last":[28],"ten":[29],"years":[30],"(2011-2021).":[31],"The":[32,164],"selection":[33,58],"criteria":[34],"includes":[35],"(a)":[36],"type":[37],"AAI":[39,131,169],"-":[40,52,80,112,129],"Speaker":[41,44],"Dependent":[42],"and":[43,59,69,72,85,102,117,152,159,175,198],"Independent":[45],"AAI,":[46],"(b)":[47],"objectives":[48],"work":[51],"Articulatory":[53,55],"approximation,":[54],"Feature":[56],"space":[57],"Automatic":[60],"Speech":[61],"Recognition":[62],"(ASR),":[63],"explore":[64],"correlation":[66],"between":[67],"acoustic":[68],"articulatory":[70,182],"features,":[71],"framework":[73],"for":[74,201],"Computer-assisted":[75],"language":[76],"training,":[77],"(c)":[78],"Corpus":[79],"Simultaneously":[81],"recorded":[82],"speech":[83,199],"(wav)":[84],"medical":[86],"imaging":[87],"models":[88,111],"such":[89],"as":[90,130],"ElectroMagnetic":[91],"Articulography":[92],"(EMA),":[93],"Electropalatography":[94],"(EPG),":[95],"Laryngography,":[96],"Electroglottography":[97],"(EGG),":[98],"X-ray":[99],"Cineradiography,":[100],"Ultrasound,":[101],"real-time":[103],"Magnetic":[104],"Resonance":[105],"Imaging":[106],"(rtMRI),":[107],"(d)":[108],"Methods":[109],"or":[110],"recent":[113],"are":[115,122],"considered,":[116],"therefore":[118],"all":[119],"based":[123],"machine":[125],"learning,":[126],"(e)":[127],"Evaluation":[128],"a":[133,173],"non-linear":[134],"regression":[135],"problem,":[136],"performance":[138],"evaluation":[139],"mostly":[141],"done":[142],"by":[143],"Correlation":[144],"Coefficient":[145],"(CC),":[146],"Root":[147],"Mean":[148,155,160],"Square":[149,156],"Error":[150,157,162],"(RMSE),":[151],"also":[153],"(MSE),":[158],"Format":[161],"(MFE).":[163],"practical":[165],"application":[166],"model":[170],"can":[171,191],"provide":[172,195],"better":[174],"user-friendly":[176],"interpretable":[177],"image":[178],"feedback":[179,189],"system":[180,190],"positions,":[183],"especially":[184],"tongue":[185],"movement.":[186],"Such":[187],"trajectory":[188],"be":[192],"used":[193],"to":[194],"phonetic,":[196],"language,":[197],"therapy":[200],"pathological":[202],"subjects.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}
