{"id":"https://openalex.org/W7207799528","doi":"https://doi.org/10.31234/osf.io/s57tz_v2","title":"Alzheimer's Disease Detection via Large Pre-Trained Speech and Language Models: Taxonomy, Progress, and Open Challenges","display_name":"Alzheimer's Disease Detection via Large Pre-Trained Speech and Language Models: Taxonomy, Progress, and Open Challenges","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7207799528","doi":"https://doi.org/10.31234/osf.io/s57tz_v2"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/s57tz_v2","doi":"https://doi.org/10.31234/osf.io/s57tz_v2","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/s57tz_v2","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/s57tz_v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005643073","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0003-4266-2005","observed_orcids":["https://orcid.org/0000-0003-4266-2005","https://orcid.org/0000-0002-9490-8209"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan-Chao Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4266-2005","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149736254","display_name":"Yilin Pan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilin Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051501323","display_name":"Yin-Long Liu","orcid":"https://orcid.org/0009-0004-0380-0836","observed_orcids":["https://orcid.org/0009-0004-0380-0836"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin-Long Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149671895","display_name":"Liu He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149753810","display_name":"Qi Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149513797","display_name":"Siyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149587903","display_name":"Wei-Qiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060851208","display_name":"Saturnino F. Luz","orcid":"https://orcid.org/0000-0001-8430-7875","observed_orcids":["https://orcid.org/0000-0001-8430-7875"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saturnino Luz","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0001-8430-7875","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149564686","display_name":"Zhenhua Ling","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134116075","display_name":"Jiahong Yuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T10009","display_name":"Dementia and Cognitive Impairment Research","score":0.548799991607666,"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"}},"topics":[{"id":"https://openalex.org/T10009","display_name":"Dementia and Cognitive Impairment Research","score":0.548799991607666,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.3449999988079071,"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/T10863","display_name":"Voice and Speech Disorders","score":0.027799999341368675,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/alzheimer-s-disease-detection","display_name":"Alzheimer's disease detection","score":0.9980000257492065},{"id":"https://openalex.org/keywords/large-pre-trained-models","display_name":"large pre-trained models","score":0.7319999933242798},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.9240000247955322},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.9459999799728394},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8230000138282776},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.9559999704360962},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.6430000066757202},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.7139999866485596},{"id":"https://openalex.org/keywords/dementia-assessment","display_name":"dementia assessment","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398999929428101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531000018119812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3677999973297119},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.26579999923706055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.31234/osf.io/s57tz_v2","doi":"https://doi.org/10.31234/osf.io/s57tz_v2","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/s57tz_v2","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:share.osf.io:95b7d5cb-b763-47ec-a4f0-bd77b97b20c8","doi":null,"is_oa":true,"landing_page_url":"https://osf.io/s57tz","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.31234/osf.io/s57tz_v2","doi":"https://doi.org/10.31234/osf.io/s57tz_v2","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/s57tz_v2","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.8048999905586243}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3157651102","https://openalex.org/W4372259936","https://openalex.org/W7084093982","https://openalex.org/W4405709833","https://openalex.org/W4401854677","https://openalex.org/W4287118087","https://openalex.org/W7118067457","https://openalex.org/W3047016605","https://openalex.org/W4415068104","https://openalex.org/W4404780785"],"abstract_inverted_index":{"Alzheimer's":[0],"Disease":[1],"(AD)":[2],"detection":[3,38,102],"from":[4,124,156],"spoken":[5],"language":[6,18,95],"has":[7],"advanced":[8],"considerably":[9],"with":[10,116],"the":[11,45,132],"rise":[12],"of":[13,89],"large":[14,91],"pre-trained":[15,58,92,127],"speech":[16,93],"and":[17,26,72,81,94,103,147,159,178,188,197],"models,":[19],"including":[20],"wav2vec":[21],"2.0,":[22],"BERT,":[23],"generative":[24],"LLMs,":[25],"emerging":[27],"audio-LLMs.":[28],"These":[29],"models":[30,96,114],"often":[31],"report":[32],"higher":[33],"performance":[34,73],"on":[35],"shared":[36,157],"AD":[37,101,174,184],"benchmarks":[39,158],"than":[40],"handcrafted-feature":[41],"pipelines,":[42],"while":[43],"reducing":[44],"need":[46],"for":[47,100,173,183],"manual":[48],"feature":[49],"design.":[50],"Yet":[51],"their":[52],"advantages":[53,179],"remain":[54],"difficult":[55],"to":[56,162],"interpret:":[57],"representations":[59],"are":[60,67,171],"largely":[61],"a":[62,87],"black":[63],"box,":[64],"benchmark":[65],"gains":[66],"not":[68],"always":[69],"statistically":[70],"robust,":[71],"can":[74],"vary":[75],"substantially":[76],"across":[77],"languages,":[78],"elicitation":[79],"protocols,":[80],"clinical":[82],"task":[83],"definitions.This":[84],"survey":[85],"proposes":[86],"taxonomy":[88,167],"how":[90,169],"have":[97],"been":[98],"used":[99,172],"progression-related":[104],"tasks.":[105],"We":[106,129],"define":[107],"Large":[108],"Pre-trained":[109],"Models":[110],"(LPMs)":[111],"as":[112],"Transformer-based":[113],"trained":[115],"self-supervised":[117],"or":[118],"weakly":[119],"supervised":[120],"objectives,":[121],"distinguishing":[122],"them":[123],"earlier":[125],"non-Transformer":[126],"representations.":[128],"then":[130],"organize":[131],"literature":[133],"into":[134],"six":[135],"usage":[136],"strategies:":[137],"direct":[138],"application,":[139],"fine-tuning,":[140],"transfer":[141],"learning,":[142,144],"multitask":[143],"multilingual":[145],"modeling,":[146],"generative-LLM-based":[148],"assessment.":[149],"Across":[150],"these":[151],"categories,":[152],"we":[153],"synthesize":[154],"evidence":[155],"recent":[160],"studies":[161],"answer":[163],"four":[164],"questions:1)":[165],"what":[166,176,186,194],"captures":[168],"LPMs":[170,181,191],"detection;2)":[175],"progress":[177],"do":[180,190],"offer":[182],"detection;3)":[185],"challenges":[187],"limitations":[189],"exhibit;":[192],"and4)":[193],"future":[195],"opportunities":[196],"open":[198],"tasks":[199],"they":[200],"present.":[201]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-04T00:00:00"}