{"id":"https://openalex.org/W4225270920","doi":"https://doi.org/10.1109/icassp43922.2022.9747054","title":"Dementia Detection by Fusing Speech and Eye-Tracking Representation","display_name":"Dementia Detection by Fusing Speech and Eye-Tracking Representation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225270920","doi":"https://doi.org/10.1109/icassp43922.2022.9747054"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747054","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5004434747","display_name":"Zheng-Yan Sheng","orcid":"https://orcid.org/0009-0002-0638-5530"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyan Sheng","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007911614","display_name":"Zhiqiang Guo","orcid":"https://orcid.org/0000-0001-9393-4854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Guo","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354075","display_name":"Xin Li","orcid":"https://orcid.org/0000-0003-4521-446X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","iFlytek Research, Hefei, P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"iFlytek Research, Hefei, P.R.China","institution_ids":[]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626399","display_name":"Yunxia Li","orcid":"https://orcid.org/0000-0002-0626-2584"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I4210160344","display_name":"Tongji Hospital","ror":"https://ror.org/04xy45965","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210160344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxia Li","raw_affiliation_strings":["Tongji University School of Medicine,Shanghai Tongji Hospital,Shanghai,China","Shanghai Tongji Hospital, Tongji University School of Medicine, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University School of Medicine,Shanghai Tongji Hospital,Shanghai,China","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I4210160344"]},{"raw_affiliation_string":"Shanghai Tongji Hospital, Tongji University School of Medicine, Shanghai, China","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I4210160344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6457","last_page":"6461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10009","display_name":"Dementia and Cognitive Impairment Research","score":0.989799976348877,"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":0.989799976348877,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9890000224113464,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7763875722885132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6246891021728516},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5896503925323486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.573760986328125},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5352775454521179},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44697627425193787},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4329751133918762},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.431557297706604},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.411734402179718},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3797694146633148},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10783237218856812},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0741986632347107},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.0668986439704895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763875722885132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6246891021728516},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5896503925323486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573760986328125},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5352775454521179},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44697627425193787},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4329751133918762},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.431557297706604},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.411734402179718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3797694146633148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10783237218856812},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0741986632347107},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0668986439704895},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747054","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1600451534","https://openalex.org/W1853705225","https://openalex.org/W1971583858","https://openalex.org/W2012897754","https://openalex.org/W2047509901","https://openalex.org/W2074037951","https://openalex.org/W2115017507","https://openalex.org/W2158516192","https://openalex.org/W2239141610","https://openalex.org/W2401240531","https://openalex.org/W2610961739","https://openalex.org/W2739382680","https://openalex.org/W2775724624","https://openalex.org/W2889065492","https://openalex.org/W2890952074","https://openalex.org/W2964051877","https://openalex.org/W2972983216","https://openalex.org/W3012419921","https://openalex.org/W3029634315","https://openalex.org/W3037437335","https://openalex.org/W3113283374","https://openalex.org/W3161417069","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6754392867"],"related_works":["https://openalex.org/W2552023628","https://openalex.org/W2357461155","https://openalex.org/W2384129116","https://openalex.org/W2275988210","https://openalex.org/W4224255737","https://openalex.org/W2539985974","https://openalex.org/W2892009249","https://openalex.org/W2897067191","https://openalex.org/W4312658081","https://openalex.org/W4224942917"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,18,48,68,76],"method":[4,93],"of":[5,15,90],"detecting":[6],"dementia":[7,60],"from":[8,62],"the":[9,87,91],"simultaneous":[10],"speech":[11,24,43,105],"and":[12,27,44,75,100],"eye-tracking":[13,45,107],"recordings":[14],"subjects":[16],"in":[17],"picture":[19,29],"description":[20],"task.":[21],"First,":[22],"automatic":[23],"recognition":[25,30],"(ASR)":[26],"regional":[28],"(RPR)":[31],"models":[32,102],"are":[33],"built":[34],"to":[35,53],"extract":[36],"content-related":[37],"bottleneck":[38],"(BN)":[39],"features":[40],"for":[41,58,72,80],"both":[42],"inputs.":[46],"Then,":[47],"neural":[49],"network":[50,66],"is":[51,94],"designed":[52],"fuse":[54],"these":[55],"two":[56],"modals":[57],"discriminating":[59],"patients":[61],"healthy":[63],"controls.":[64],"The":[65],"contains":[67],"cross-modal":[69],"Transformer":[70,78],"encoder":[71,79],"bimodal":[73],"interaction,":[74],"self-attention":[77],"final":[81],"classification.":[82],"Experimental":[83],"results":[84],"demonstrate":[85],"that":[86],"detection":[88],"accuracy":[89],"proposed":[92],"84.26%,":[95],"which":[96],"outperforms":[97],"baseline":[98],"methods":[99],"ablated":[101],"using":[103],"single":[104],"or":[106],"input.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}