{"id":"https://openalex.org/W4308216426","doi":"https://doi.org/10.1109/bhi56158.2022.9926818","title":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","display_name":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","publication_year":2022,"publication_date":"2022-09-27","ids":{"openalex":"https://openalex.org/W4308216426","doi":"https://doi.org/10.1109/bhi56158.2022.9926818"},"language":"en","primary_location":{"id":"doi:10.1109/bhi56158.2022.9926818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi56158.2022.9926818","pdf_url":null,"source":{"id":"https://openalex.org/S4363608521","display_name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.04368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027752295","display_name":"Loukas Ilias","orcid":"https://orcid.org/0000-0002-4483-4264"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Loukas Ilias","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens,Decision Support Systems Laboratory,Athens,Greece,15780"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens,Decision Support Systems Laboratory,Athens,Greece,15780","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015748230","display_name":"Dimitris Askounis","orcid":"https://orcid.org/0000-0002-2618-5715"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitris Askounis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens,Decision Support Systems Laboratory,Athens,Greece,15780"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens,Decision Support Systems Laboratory,Athens,Greece,15780","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113725247","display_name":"John Psarras","orcid":"https://orcid.org/0000-0002-3104-9144"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"John Psarras","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens,Decision Support Systems Laboratory,Athens,Greece,15780"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens,Decision Support Systems Laboratory,Athens,Greece,15780","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0894,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79918162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9977999925613403,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.6944491863250732},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.666486382484436},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5446812510490417},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47067293524742126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4490337371826172},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4460848867893219},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4181455075740814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35659193992614746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35449832677841187},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08234471082687378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944491863250732},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.666486382484436},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5446812510490417},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47067293524742126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490337371826172},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4460848867893219},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4181455075740814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35659193992614746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35449832677841187},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08234471082687378},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bhi56158.2022.9926818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi56158.2022.9926818","pdf_url":null,"source":{"id":"https://openalex.org/S4363608521","display_name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2211.04368","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.04368","pdf_url":"https://arxiv.org/pdf/2211.04368","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.04368","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.04368","pdf_url":"https://arxiv.org/pdf/2211.04368","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2056323522","https://openalex.org/W2074037951","https://openalex.org/W2085662862","https://openalex.org/W2740956487","https://openalex.org/W2896457183","https://openalex.org/W2964010806","https://openalex.org/W2968543045","https://openalex.org/W2979826702","https://openalex.org/W3094726021","https://openalex.org/W3094848124","https://openalex.org/W3094909210","https://openalex.org/W3095738426","https://openalex.org/W3096609969","https://openalex.org/W3096812425","https://openalex.org/W3097109903","https://openalex.org/W3097288651","https://openalex.org/W3097641059","https://openalex.org/W3097779478","https://openalex.org/W3106959347","https://openalex.org/W3128781814","https://openalex.org/W3129165846","https://openalex.org/W3138516171","https://openalex.org/W3154143698","https://openalex.org/W3163938617","https://openalex.org/W4235242162","https://openalex.org/W4295312788","https://openalex.org/W4297206627","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6767494712"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Alzheimer's":[0],"disease":[1],"(AD)":[2],"is":[3,18,104,122,137],"a":[4,48,125,130,140,170],"progressive":[5],"neurological":[6],"disorder,":[7],"meaning":[8],"that":[9,188],"the":[10,15,20,63,95,160,164,176,183],"symptoms":[11],"develop":[12],"gradually":[13],"throughout":[14],"years.":[16],"It":[17],"also":[19,154],"main":[21],"cause":[22],"of":[23,110],"dementia,":[24],"which":[25,84],"affects":[26],"memory,":[27],"thinking":[28],"skills,":[29],"and":[30,65,68,71,93,97,117,201,206],"mental":[31],"abilities.":[32],"Nowadays,":[33],"researchers":[34],"have":[35],"moved":[36],"their":[37],"interest":[38],"towards":[39],"AD":[40],"detection":[41],"from":[42,155,163],"spontaneous":[43],"speech,":[44],"since":[45],"it":[46],"constitutes":[47],"time-effective":[49],"procedure.":[50],"However,":[51],"existing":[52,196],"state-of-the-art":[53],"works":[54],"proposing":[55],"multimodal":[56],"approaches":[57,191],"do":[58],"not":[59],"take":[60],"into":[61],"consideration":[62],"inter-":[64,96],"intra-modal":[66,98],"interactions":[67],"propose":[69,80],"early":[70],"late":[72],"fusion":[73,172],"approaches.":[74],"To":[75],"tackle":[76],"these":[77],"limitations,":[78],"we":[79],"deep":[81],"neural":[82],"networks,":[83],"can":[85],"be":[86],"trained":[87],"in":[88],"an":[89,107,145],"end-to-end":[90],"trainable":[91],"way":[92],"capture":[94],"interactions.":[99,178],"Firstly,":[100],"each":[101,120,135,156],"audio":[102,157],"file":[103],"converted":[105],"to":[106,169,204],"image":[108,136],"consisting":[109],"three":[111],"channels,":[112],"i.e.,":[113],"log-Mel":[114],"spectrogram,":[115],"delta,":[116],"delta-delta.":[118],"Next,":[119],"transcript":[121],"passed":[123,138],"through":[124,139],"BERT":[126],"model":[127],"followed":[128,143],"by":[129,144],"gated":[131,147],"self-attention":[132,148],"layer.":[133,149],"Similarly,":[134],"Swin":[141],"Transformer":[142],"independent":[146],"Acoustic":[150],"features":[151],"are":[152,167],"extracted":[153],"file.":[158],"Finally,":[159],"representation":[161],"vectors":[162],"different":[165],"modalities":[166],"fed":[168],"tensor":[171],"layer":[173],"for":[174],"capturing":[175],"inter-modal":[177],"Extensive":[179],"experiments":[180],"conducted":[181],"on":[182],"ADReSS":[184],"Challenge":[185],"dataset":[186],"indicate":[187],"our":[189],"introduced":[190],"obtain":[192],"valuable":[193],"advantages":[194],"over":[195],"research":[197],"initiatives":[198],"reaching":[199],"Accuracy":[200],"F1-score":[202],"up":[203],"86.25%":[205],"85.48%":[207],"respectively.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}