{"id":"https://openalex.org/W4392902798","doi":"https://doi.org/10.1109/icassp48485.2024.10448004","title":"Whisper-Based Transfer Learning for Alzheimer Disease Classification: Leveraging Speech Segments with Full Transcripts as Prompts","display_name":"Whisper-Based Transfer Learning for Alzheimer Disease Classification: Leveraging Speech Segments with Full Transcripts as Prompts","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902798","doi":"https://doi.org/10.1109/icassp48485.2024.10448004"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5100782321","display_name":"Jinpeng Li","orcid":"https://orcid.org/0000-0002-0633-6184"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinpeng Li","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100782321"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.0712,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94302355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11211","last_page":"11215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7950190305709839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6429771184921265},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6144299507141113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5540880560874939},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5424398183822632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112333297729492},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5067821145057678},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42523622512817383},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.42215704917907715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950190305709839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6429771184921265},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6144299507141113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5540880560874939},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5424398183822632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112333297729492},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5067821145057678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42523622512817383},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.42215704917907715},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1014351457","display_name":null,"funder_award_id":"62276153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2239141610","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2965373594","https://openalex.org/W3036601975","https://openalex.org/W3097533615","https://openalex.org/W3154143698","https://openalex.org/W3196495667","https://openalex.org/W3198116506","https://openalex.org/W4311000453","https://openalex.org/W4311059915","https://openalex.org/W4312091558","https://openalex.org/W4372259936","https://openalex.org/W4385807419","https://openalex.org/W4385807453","https://openalex.org/W4385823266","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W4282827391","https://openalex.org/W4386828785","https://openalex.org/W3165580226","https://openalex.org/W3135401135","https://openalex.org/W2886688859","https://openalex.org/W3133164560","https://openalex.org/W3041001745","https://openalex.org/W4224526119","https://openalex.org/W2791025012"],"abstract_inverted_index":{"Alzheimer\u2019s":[0,40],"disease":[1,41],"(AD)":[2],"is":[3,15,23],"a":[4,25,87,99,108],"neurodegenerative":[5],"disorder":[6],"that":[7],"can":[8],"lead":[9],"to":[10,55,77,89],"speech":[11,47,93,137],"impairments.":[12],"Early":[13],"diagnosis":[14,22],"crucial":[16],"for":[17,39,105],"effective":[18],"treatment,":[19],"and":[20,49,120,126,134],"speech-based":[21],"currently":[24],"hot":[26],"research":[27],"topic.":[28],"In":[29,53],"this":[30,79],"study,":[31],"we":[32,72],"explore":[33],"the":[34,44,57,65,83,114,118,131],"feasibility":[35],"of":[36,59,103,111],"transfer":[37],"learning":[38],"detection":[42],"using":[43,82],"state-of-the-art":[45],"multilingual":[46],"recognition":[48],"translation":[50],"model:":[51],"Whisper.":[52],"order":[54],"address":[56],"limitation":[58],"Whisper\u2019s":[60],"narrow":[61],"perspective":[62],"caused":[63],"by":[64,81],"restricted":[66],"audio":[67],"segment":[68],"length":[69],"during":[70],"fine-tuning,":[71],"propose":[73],"an":[74],"innovative":[75],"method":[76],"overcome":[78],"problem":[80],"full":[84],"transcript":[85],"as":[86],"prompt":[88],"assist":[90],"in":[91,98],"training":[92],"segments.":[94],"This":[95],"approach":[96],"results":[97],"relative":[100],"performance":[101],"improvement":[102],"9%-12%":[104],"models":[106],"with":[107],"higher":[109],"number":[110],"parameters.":[112],"On":[113],"ADReSSo":[115],"test":[116],"set,":[117],"accuracy":[119],"F1":[121],"score":[122],"achieved":[123],"are":[124],"84.51%":[125],"84.50%":[127],"respectively,":[128],"surpassing":[129],"both":[130],"baseline":[132],"system":[133],"commonly":[135],"used":[136],"recognition-language":[138],"model":[139],"cascade":[140],"methods,":[141],"demonstrating":[142],"its":[143],"effectiveness.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}