{"id":"https://openalex.org/W4402111420","doi":"https://doi.org/10.21437/interspeech.2024-2063","title":"Segmental and Suprasegmental Speech Foundation Models for Classifying Cognitive Risk Factors: Evaluating Out-of-the-Box Performance","display_name":"Segmental and Suprasegmental Speech Foundation Models for Classifying Cognitive Risk Factors: Evaluating Out-of-the-Box Performance","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111420","doi":"https://doi.org/10.21437/interspeech.2024-2063","pmid":"https://pubmed.ncbi.nlm.nih.gov/40051645"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2063","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-2063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11884505/pdf/nihms-2056086.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028387113","display_name":"Si-Ioi Ng","orcid":"https://orcid.org/0000-0002-7429-7391"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Si-Ioi Ng","raw_affiliation_strings":["Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102873271","display_name":"Lingfeng Xu","orcid":"https://orcid.org/0000-0002-6554-9438"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingfeng Xu","raw_affiliation_strings":["Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103158889","display_name":"Kimberly D. Mueller","orcid":"https://orcid.org/0000-0001-8691-9517"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kimberly D. Mueller","raw_affiliation_strings":["University of Wisconsin-Madison, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056934840","display_name":"Julie Liss","orcid":"https://orcid.org/0000-0001-8782-2901"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Liss","raw_affiliation_strings":["Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028387113"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19303871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2024","issue":null,"first_page":"917","last_page":"921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.8549000024795532,"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":0.8549000024795532,"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/T10009","display_name":"Dementia and Cognitive Impairment Research","score":0.8202000260353088,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"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/T11358","display_name":"Dysphagia Assessment and Management","score":0.722100019454956,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6016113758087158},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5691996216773987},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5474416017532349},{"id":"https://openalex.org/keywords/intraclass-correlation","display_name":"Intraclass correlation","score":0.5365393757820129},{"id":"https://openalex.org/keywords/dementia","display_name":"Dementia","score":0.5278715491294861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.511790931224823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.456277996301651},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.45262664556503296},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.44140681624412537},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.43623125553131104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3535027503967285},{"id":"https://openalex.org/keywords/developmental-psychology","display_name":"Developmental psychology","score":0.2053336799144745},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.19832122325897217},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1969776153564453},{"id":"https://openalex.org/keywords/psychometrics","display_name":"Psychometrics","score":0.15943250060081482},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.08711233735084534}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6016113758087158},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5691996216773987},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5474416017532349},{"id":"https://openalex.org/C104709138","wikidata":"https://www.wikidata.org/wiki/Q1671540","display_name":"Intraclass correlation","level":3,"score":0.5365393757820129},{"id":"https://openalex.org/C2779483572","wikidata":"https://www.wikidata.org/wiki/Q83030","display_name":"Dementia","level":3,"score":0.5278715491294861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.511790931224823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.456277996301651},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.45262664556503296},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.44140681624412537},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.43623125553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3535027503967285},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.2053336799144745},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.19832122325897217},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1969776153564453},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.15943250060081482},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.08711233735084534},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-2063","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-2063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmid:40051645","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40051645","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":"Interspeech","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11884505","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11884505","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11884505/pdf/nihms-2056086.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:11884505","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11884505","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11884505/pdf/nihms-2056086.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111420.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2049420167","https://openalex.org/W77735594","https://openalex.org/W79086181","https://openalex.org/W1963758283","https://openalex.org/W2323976173","https://openalex.org/W2097209223","https://openalex.org/W2050552023","https://openalex.org/W2032920816","https://openalex.org/W2077437308","https://openalex.org/W2237649353"],"abstract_inverted_index":{"Speech":[0],"foundation":[1],"models":[2,33,131],"are":[3],"remarkably":[4],"successful":[5],"in":[6,54,105],"various":[7],"consumer":[8],"applications,":[9],"prompting":[10],"their":[11],"extension":[12],"to":[13,34],"clinical":[14,21,136],"use-cases.":[15],"This":[16],"is":[17],"challenged":[18],"by":[19,37],"small":[20],"datasets,":[22],"which":[23],"precludes":[24],"effective":[25],"fine-tuning.":[26],"We":[27],"tested":[28],"the":[29,55],"efficacy":[30],"of":[31,57,77,100,117,124,129],"two":[32],"classify":[35],"participants":[36],"segmental":[38],"(Wav2Vec2.0)":[39],"and":[40,79,88,103,112,119,126,139],"suprasegmental":[41],"(Trillsson)":[42],"speech":[43,137],"analysis":[44,138],"windows.":[45],"Analysis":[46],"at":[47],"both":[48],"time":[49],"scales":[50],"has":[51],"shown":[52],"differences":[53],"context":[56],"cognitive":[58,70],"decline.":[59],"Speakers":[60],"were":[61,106],"classified":[62],"as":[63],"healthy":[64],"controls":[65],"(HC),":[66],"Amyloid-\u03b2+":[67],"(A\u03b2+),":[68],"mild":[69],"impairment":[71],"(MCI),":[72],"or":[73],"dementia.":[74],"A":[75],"subset":[76],"W2V2":[78,94,120],"Trillsson":[80,118],"representations":[81],"showed":[82,93,121],"large":[83],"effect":[84],"size":[85],"between":[86],"HC":[87],"each":[89],"risk":[90],"factor.":[91],"Cross-validation":[92],"consistently":[95],"outperforms":[96],"Trillsson.":[97],"Mean":[98],"macro-F1":[99],"54.1%,":[101],"63.5%,":[102],"72.0%":[104],"found":[107],"for":[108,135],"classifying":[109],"A\u03b2+,":[110],"MCI,":[111],"dementia":[113],"from":[114],"HC.":[115],"Repeatability":[116],"intraclass":[122],"correlations":[123],"0.30":[125],"0.41.":[127],"Reliability":[128],"such":[130],"must":[132],"be":[133],"enhanced":[134],"longitudinal":[140],"tracking.":[141]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
