{"id":"https://openalex.org/W4415432969","doi":"https://doi.org/10.21437/interspeech.2025-2387","title":"Enhancing Acoustic-to-Articulatory Speech Inversion by Incorporating Nasality","display_name":"Enhancing Acoustic-to-Articulatory Speech Inversion by Incorporating Nasality","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432969","doi":"https://doi.org/10.21437/interspeech.2025-2387"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2387","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.09231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120093796","display_name":"Saba Tabatabaee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saba Tabatabaee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047627556","display_name":"Suzanne Boyce","orcid":"https://orcid.org/0000-0003-2105-2486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzanne Boyce","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010373518","display_name":"Liran Oren","orcid":"https://orcid.org/0000-0002-3232-6799"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liran Oren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013202273","display_name":"Mark Tiede","orcid":"https://orcid.org/0000-0002-6118-0776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Tiede","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carol Espy-Wilson","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120093796"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0687,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89505503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9254000186920166,"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":0.9254000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nasality","display_name":"Nasality","score":0.8981999754905701},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8080000281333923},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.54339998960495},{"id":"https://openalex.org/keywords/nasalization","display_name":"Nasalization","score":0.5303000211715698},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.5214999914169312},{"id":"https://openalex.org/keywords/aperiodic-graph","display_name":"Aperiodic graph","score":0.46050000190734863},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C2780256294","wikidata":"https://www.wikidata.org/wiki/Q15946863","display_name":"Nasality","level":3,"score":0.8981999754905701},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8080000281333923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6305000185966492},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C516976414","wikidata":"https://www.wikidata.org/wiki/Q1606582","display_name":"Nasalization","level":3,"score":0.5303000211715698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5238000154495239},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C104247578","wikidata":"https://www.wikidata.org/wiki/Q4779368","display_name":"Aperiodic graph","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36649999022483826},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C2780336059","wikidata":"https://www.wikidata.org/wiki/Q215558","display_name":"Vocal folds","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C178992907","wikidata":"https://www.wikidata.org/wiki/Q1806413","display_name":"Electroglottograph","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2700999975204468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2387","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.09231","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09231","pdf_url":"https://arxiv.org/pdf/2506.09231","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2506.09231","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09231","pdf_url":"https://arxiv.org/pdf/2506.09231","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0,19],"is":[1],"produced":[2],"through":[3],"the":[4,59,138],"coordination":[5],"of":[6,58,125],"vocal":[7],"tract":[8,34],"constricting":[9],"organs:":[10],"lips,":[11],"tongue,":[12],"velum,":[13],"and":[14,29,46,49,73,103,106,114,131],"glottis.":[15],"Previous":[16],"works":[17],"developed":[18],"Inversion":[20],"(SI)":[21],"systems":[22],"to":[23,137],"recover":[24],"acoustic-to-articulatory":[25],"mappings":[26],"for":[27,54,86],"lip":[28],"tongue":[30],"constrictions,":[31],"called":[32],"oral":[33,101,112,128],"variables":[35],"(TVs),":[36],"which":[37],"were":[38],"later":[39],"enhanced":[40],"by":[41],"including":[42],"source":[43,115],"information":[44],"(periodic":[45],"aperiodic":[47],"energies,":[48],"F0":[50],"frequency)":[51],"as":[52,70],"proxies":[53],"glottal":[55],"control.":[56],"Comparison":[57],"nasometric":[60],"measures":[61],"with":[62,79,117],"high-speed":[63],"nasopharyngoscopy":[64],"showed":[65],"that":[66,74,99,110],"nasalance":[67,104,134],"can":[68],"serve":[69],"ground":[71],"truth,":[72],"an":[75],"SI":[76,92],"system":[77],"trained":[78],"it":[80],"reliably":[81],"recovers":[82],"velum":[83],"movement":[84],"patterns":[85],"American":[87],"English":[88],"speakers.":[89],"Here,":[90],"two":[91],"training":[93],"approaches":[94],"are":[95],"compared:":[96],"baseline":[97,139],"models":[98],"estimate":[100],"TVs":[102,113,129],"independently,":[105],"a":[107],"synergistic":[108,120],"model":[109,121],"combines":[111],"features":[116],"nasalance.":[118],"The":[119],"shows":[122],"relative":[123],"improvements":[124],"5%":[126],"in":[127,133],"estimation":[130,135],"9%":[132],"compared":[136],"models.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-23T00:00:00"}
