{"id":"https://openalex.org/W7123886888","doi":"https://doi.org/10.1109/iscc65549.2025.11325956","title":"Enhancing Alzheimer\u2019s Diagnosis Through Spontaneous Speech Recognition: Deep Learning Approach with Data Augmentation","display_name":"Enhancing Alzheimer\u2019s Diagnosis Through Spontaneous Speech Recognition: Deep Learning Approach with Data Augmentation","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W7123886888","doi":"https://doi.org/10.1109/iscc65549.2025.11325956"},"language":null,"primary_location":{"id":"doi:10.1109/iscc65549.2025.11325956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc65549.2025.11325956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Symposium on Computers and Communications (ISCC)","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/A5120499597","display_name":"Venkata Sai Bhargav Mutala","orcid":null},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkata Sai Bhargav Mutala","raw_affiliation_strings":["Kennesaw State University,Department of Information and Technology,Marietta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University,Department of Information and Technology,Marietta,GA,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070223983","display_name":"Seyedamin Pouriyeh","orcid":"https://orcid.org/0000-0002-5746-2914"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyedamin Pouriyeh","raw_affiliation_strings":["Kennesaw State University,Department of Information and Technology,Marietta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University,Department of Information and Technology,Marietta,GA,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101238218","display_name":"Chloe Yixin Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chloe Yixin Xie","raw_affiliation_strings":["Kennesaw State University,Department of Information and Technology,Marietta,GA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University,Department of Information and Technology,Marietta,GA,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033472348","display_name":"Meng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Han","raw_affiliation_strings":["Binjiang Institute of Zhejiang University,Hangzhou,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binjiang Institute of Zhejiang University,Hangzhou,Zhejiang,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106494984","display_name":"Ilaria Basile","orcid":"https://orcid.org/0009-0002-8158-1363"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ilaria Basile","raw_affiliation_strings":["Institute for High-Performance Computing and Networking (ICAR) National Research Council (CNR),Naples,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for High-Performance Computing and Networking (ICAR) National Research Council (CNR),Naples,Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122946242","display_name":"Giovanna Sannino","orcid":null},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanna Sannino","raw_affiliation_strings":["Institute for High-Performance Computing and Networking (ICAR) National Research Council (CNR),Naples,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for High-Performance Computing and Networking (ICAR) National Research Council (CNR),Naples,Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.844,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80700386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.35850000381469727,"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":0.35850000381469727,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.21539999544620514,"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/T11358","display_name":"Dysphagia Assessment and Management","score":0.049800001084804535,"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/deep-learning","display_name":"Deep learning","score":0.7854999899864197},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7067999839782715},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5174999833106995},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48240000009536743},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.447299987077713},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41040000319480896},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4034000039100647}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7854999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7319999933242798},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7067999839782715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894000172615051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5680000185966492},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48240000009536743},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4011000096797943},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscc65549.2025.11325956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc65549.2025.11325956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Symposium on Computers and Communications (ISCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2936774411","https://openalex.org/W2951442257","https://openalex.org/W2963723765","https://openalex.org/W2970737019","https://openalex.org/W2999941287","https://openalex.org/W3011702533","https://openalex.org/W3012303644","https://openalex.org/W3115928614","https://openalex.org/W3145157056","https://openalex.org/W3212684309","https://openalex.org/W4281493160","https://openalex.org/W4311496987","https://openalex.org/W4317934405","https://openalex.org/W4388742908","https://openalex.org/W4400834464"],"related_works":[],"abstract_inverted_index":{"Alzheimer\u2019s":[0,165],"disease":[1],"(AD)":[2],"represents":[3],"a":[4,99,127],"major":[5],"public":[6],"health":[7],"challenge":[8],"due":[9],"to":[10,174],"its":[11],"irreversible":[12],"progression":[13],"and":[14,25,31,71,102,110,136,143,161,167],"increasing":[15],"prevalence":[16],"among":[17],"the":[18,56,60,94,116,133,152,169],"aging":[19],"population.":[20],"Early":[21],"diagnosis":[22,166],"is":[23],"crucial,":[24],"recent":[26],"advances":[27],"in":[28,38,89],"Artificial":[29],"Intelligence":[30],"data":[32,58,69,78,172],"analytics":[33],"have":[34],"shown":[35],"promising":[36],"results":[37,113],"detection":[39,54],"methods.":[40],"This":[41,149],"study":[42],"proposes":[43],"an":[44,122],"approach":[45],"based":[46,107],"on":[47,108],"deep":[48,155],"neural":[49],"networks":[50],"for":[51,164],"automatic":[52],"AD":[53],"from":[55],"speech":[57],"of":[59,96,124,130,154,171],"ADReSS2020":[61],"dataset,":[62],"using":[63],"log-Mel":[64],"spectrogram":[65],"representation.":[66],"To":[67],"address":[68],"limitations":[70],"enhance":[72],"model":[73,118,176],"performance,":[74],"we":[75],"applied":[76],"five":[77],"augmentation":[79],"techniques,":[80],"which":[81],"significantly":[82],"improved":[83],"accuracy":[84,123],"by":[85],"introducing":[86],"greater":[87],"variability":[88],"audio":[90],"characteristics.":[91],"We":[92],"evaluated":[93],"performance":[95],"three":[97],"models:":[98],"CNN-LSTM":[100,117],"network":[101],"two":[103],"transfer":[104],"learning":[105],"approaches":[106,158],"ResNet50":[109],"VGG16.":[111],"Experimental":[112],"showed":[114],"that":[115],"performs":[119],"best,":[120],"achieving":[121],"68%,":[125],"with":[126,139],"significant":[128],"improvement":[129],"9.67%":[131],"over":[132],"baseline.":[134],"ResNet50-LSTM":[135],"VGG16-LSTM":[137],"followed":[138],"$\\mathbf{6":[140,144],"7}":[141],"\\%$":[142,146],"6}":[145],"accuracy,":[147],"respectively.":[148],"work":[150],"demonstrates":[151],"potential":[153],"learning-based":[156],"speech-driven":[157],"as":[159],"scalable":[160],"noninvasive":[162],"tools":[163],"highlights":[168],"importance":[170],"enhancement":[173],"improve":[175],"performance.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2026-01-14T00:00:00"}