{"id":"https://openalex.org/W4416798716","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249319","title":"Multimodal Speech Analysis for Early Detection of Mild Cognitive Impairment: A Scalable Approach","display_name":"Multimodal Speech Analysis for Early Detection of Mild Cognitive Impairment: A Scalable Approach","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798716","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249319"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Muhammad Bilal","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Muhammad Bilal","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043619920","display_name":"Waleed H. Abdulla","orcid":"https://orcid.org/0000-0002-1812-4285"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Waleed Abdulla","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034020430","display_name":"Gary Cheung","orcid":"https://orcid.org/0000-0002-0239-9356"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Gary Cheung","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050134689","display_name":"Lynette J. Tippett","orcid":"https://orcid.org/0000-0003-4592-6600"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Lynette Tippett","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043278328","display_name":"Seyed Reza Shahamiri","orcid":"https://orcid.org/0000-0003-1543-5931"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Seyed Reza Shahamiri","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154130895"],"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":"2465","last_page":"2470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.17000000178813934,"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":0.17000000178813934,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.10719999670982361,"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/T10863","display_name":"Voice and Speech Disorders","score":0.10100000351667404,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5601999759674072},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5598999857902527},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4896000027656555},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47519999742507935},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4562000036239624},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.45170000195503235},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.35989999771118164},{"id":"https://openalex.org/keywords/cognitive-load","display_name":"Cognitive load","score":0.3598000109195709},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6851000189781189},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472000002861023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.35989999771118164},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2239141610","https://openalex.org/W2487211121","https://openalex.org/W2888807255","https://openalex.org/W2936774411","https://openalex.org/W2970641574","https://openalex.org/W3096912371","https://openalex.org/W4205267278","https://openalex.org/W4387514484","https://openalex.org/W4394606408","https://openalex.org/W4402111698","https://openalex.org/W4402111796","https://openalex.org/W4402112191","https://openalex.org/W4402112211","https://openalex.org/W4402112337","https://openalex.org/W4402112501","https://openalex.org/W4404599510","https://openalex.org/W4405696894","https://openalex.org/W4410538924"],"related_works":[],"abstract_inverted_index":{"Early":[0],"detection":[1],"of":[2,44,137,147],"dementia":[3,160],"is":[4],"critical":[5],"for":[6,42,157],"timely":[7],"intervention,":[8],"yet":[9],"conventional":[10],"diagnostic":[11],"methods":[12],"remain":[13],"resource":[14],"intensive":[15],"and":[16,48,72,77,86,121,153],"limited":[17,110],"in":[18],"scalability.":[19],"Speech":[20],"analysis":[21],"offers":[22],"a":[23,39,74,99],"non-invasive":[24],"alternative,":[25],"with":[26,62],"the":[27,55,65,118,145],"potential":[28],"to":[29,83],"capture":[30],"early":[31],"cognitive":[32,46],"changes.":[33],"In":[34],"this":[35],"study,":[36],"we":[37,97],"present":[38],"multimodal":[40],"approach":[41],"classification":[43],"mild":[45],"impairment":[47],"normal":[49],"control":[50],"using":[51,102],"spontaneous":[52],"speech":[53,68],"from":[54,117,127],"TAUKADIAL":[56],"Challenge":[57],"dataset.":[58],"Our":[59,129],"pipeline":[60],"begins":[61],"transcription":[63],"via":[64],"Whisper":[66,119],"automatic":[67],"recognition":[69],"(ASR)":[70],"model":[71,101,131],"applies":[73],"novel":[75],"spectrogram-level":[76],"resampling":[78],"based":[79],"data":[80],"augmentation":[81],"technique":[82],"enhance":[84],"text":[85],"audio":[87],"diversity":[88],"while":[89],"preserving":[90],"semantic":[91],"integrity.":[92],"To":[93],"represent":[94],"textual":[95],"information,":[96],"fine-tuned":[98],"RoBERTa-large":[100],"Low-Rank":[103],"Adaptation,":[104],"enabling":[105],"efficient":[106],"domain":[107],"adaptation":[108],"on":[109],"clinical":[111],"data.":[112],"Audio":[113],"embeddings":[114],"were":[115,125],"extracted":[116],"encoder,":[120],"low-level":[122],"acoustic":[123,154],"features":[124],"derived":[126],"eGeMAPS.":[128],"best":[130],"achieved":[132],"an":[133],"unweighted":[134],"average":[135],"recall":[136],"0.86,":[138],"outperforming":[139],"single-modality":[140],"baselines.":[141],"The":[142],"results":[143],"demonstrate":[144],"value":[146],"integrating":[148],"ASR,":[149],"Natural":[150],"Language":[151],"Processing,":[152],"signal":[155],"processing":[156],"robust,":[158],"scalable":[159],"screening.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}