{"id":"https://openalex.org/W4417427449","doi":"https://doi.org/10.1109/jbhi.2025.3644692","title":"Toward Robust Assessment of Pathological Voices via Combined Low-Level Descriptors and Foundation Model Representations","display_name":"Toward Robust Assessment of Pathological Voices via Combined Low-Level Descriptors and Foundation Model Representations","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4417427449","doi":"https://doi.org/10.1109/jbhi.2025.3644692","pmid":"https://pubmed.ncbi.nlm.nih.gov/41396745"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3644692","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3644692","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/jbhi.2025.3644692","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029720315","display_name":"Whenty Ariyanti","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Whenty Ariyanti","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603153","display_name":"Kuan\u2010Yu Chen","orcid":"https://orcid.org/0000-0002-6036-2199"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9656-7551","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["University of Palermo, Palermo, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0770-0507","affiliations":[{"raw_affiliation_string":"University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3599-5071","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6956-0418","affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4735,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85191073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"30","issue":"7","first_page":"6186","last_page":"6198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.996999979019165,"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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7415000200271606},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.6963000297546387},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4275999963283539},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.39070001244544983},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.382099986076355},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.37450000643730164},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7415000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732200026512146},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.6963000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101000070571899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.39070001244544983},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.25049999356269836}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013061","descriptor_name":"Speech Acoustics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013061","descriptor_name":"Speech Acoustics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013068","descriptor_name":"Speech Production Measurement","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D013068","descriptor_name":"Speech Production Measurement","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014832","descriptor_name":"Voice Disorders","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D014832","descriptor_name":"Voice Disorders","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D014832","descriptor_name":"Voice Disorders","qualifier_ui":"Q000503","qualifier_name":"physiopathology","is_major_topic":true},{"descriptor_ui":"D014832","descriptor_name":"Voice Disorders","qualifier_ui":"Q000503","qualifier_name":"physiopathology","is_major_topic":true},{"descriptor_ui":"D014833","descriptor_name":"Voice Quality","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D014833","descriptor_name":"Voice Quality","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/jbhi.2025.3644692","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3644692","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:41396745","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41396745","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE journal of biomedical and health informatics","raw_type":null},{"id":"pmh:oai:iris.unipa.it:10447/698568","is_oa":true,"landing_page_url":"https://hdl.handle.net/10447/698568","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/jbhi.2025.3644692","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3644692","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7411686940","display_name":null,"funder_award_id":"AS-IV-115-M01","funder_id":"https://openalex.org/F4320321041","funder_display_name":"Academia Sinica"}],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Perceptual":[0],"voice":[1,12,201],"quality":[2],"assessment":[3],"plays":[4],"a":[5,59],"vital":[6],"role":[7],"in":[8,144],"diagnosing":[9],"and":[10,24,30,38,68,96,117,152,158,181,198],"monitoring":[11],"disorders.Traditional":[13],"methods,":[14],"such":[15],"as":[16],"the":[17,25,45,53,135,187],"Consensus":[18],"Auditory-Perceptual":[19],"Evaluation":[20],"of":[21,146,189],"Voice":[22,54],"(CAPE-V)":[23],"Grade,":[26],"Roughness,":[27],"Breathiness,":[28],"Asthenia,":[29],"Strain":[31],"(GRBAS)":[32],"scales,":[33],"rely":[34],"on":[35,106,114],"expert":[36],"raters":[37],"are":[39,112],"prone":[40],"to":[41,74,121],"inter-rater":[42],"variability,":[43],"emphasizing":[44],"need":[46],"for":[47,179,196],"objective":[48],"solutions.":[49],"This":[50,184],"study":[51],"introduces":[52],"Quality":[55],"Assessment":[56],"Network":[57],"(VOQANet),":[58],"deep":[60],"learning":[61],"framework":[62],"that":[63,103,127],"employs":[64],"an":[65],"attention":[66],"mechanism":[67],"Speech":[69],"Foundation":[70],"Model":[71],"(SFM)":[72],"embeddings":[73,89,192],"extract":[75],"high-level":[76],"features.":[77],"To":[78],"further":[79],"enhance":[80],"performance,":[81],"we":[82],"propose":[83],"VOQANet+,":[84],"which":[85],"integrates":[86],"self-supervised":[87],"SFM":[88,191],"with":[90,161,193],"low-level":[91,194],"acoustic":[92],"descriptors-namely":[93],"jitter,":[94],"shimmer,":[95],"harmonics-to-noise":[97],"ratio":[98],"(HNR).":[99],"Unlike":[100],"previous":[101],"approaches":[102],"focus":[104],"solely":[105],"vowel-based":[107],"phonation":[108],"(PVQD-A),":[109],"our":[110],"models":[111,143],"evaluated":[113],"both":[115],"vowel-level":[116],"sentence-level":[118],"speech":[119],"(PVQD-S)":[120],"assess":[122],"generalizability.":[123],"Experimental":[124],"results":[125],"demonstrate":[126],"sentence-based":[128],"inputs":[129],"yield":[130],"higher":[131],"accuracy,":[132],"particularly":[133],"at":[134],"patient":[136],"level.":[137],"Overall,":[138],"VOQANet":[139],"consistently":[140],"outperforms":[141],"baseline":[142],"terms":[145],"root":[147],"mean":[148],"squared":[149],"error":[150],"(RMSE)":[151],"Pearson":[153],"correlation":[154],"coefficient":[155],"across":[156],"CAPE-V":[157],"GRBAS":[159],"dimensions,":[160],"VOQANet+":[162,169],"achieving":[163],"even":[164],"greater":[165],"performance":[166,172],"gains.":[167],"Additionally,":[168],"maintains":[170],"consistent":[171],"under":[173],"noisy":[174],"conditions,":[175],"suggesting":[176],"enhanced":[177],"robustness":[178],"real-world":[180],"telehealth":[182],"applications.":[183],"work":[185],"highlights":[186],"value":[188],"combining":[190],"features":[195],"accurate":[197],"robust":[199],"pathological":[200],"assessment.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-07T06:14:10.401900","created_date":"2025-12-15T00:00:00"}