{"id":"https://openalex.org/W4405709802","doi":"https://doi.org/10.1109/iscslp63861.2024.10800618","title":"Investigation of Cross Modality Feature Fusion for Audio-Visual Dysarthric Speech Assessment","display_name":"Investigation of Cross Modality Feature Fusion for Audio-Visual Dysarthric Speech Assessment","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709802","doi":"https://doi.org/10.1109/iscslp63861.2024.10800618"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100309082","display_name":"Yicong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yicong Jiang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113020902","display_name":"Youjun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youjun Chen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070596821","display_name":"Tianzi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334191","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0002-7990-9254"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034654931","display_name":"Feng Tian","orcid":"https://orcid.org/0000-0002-6598-419X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Tian","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100309082"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33965135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9767000079154968,"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":0.9767000079154968,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9258999824523926,"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/T10860","display_name":"Speech and Audio Processing","score":0.9072999954223633,"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":0.7033724188804626},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6899077892303467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6866728067398071},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5867984890937805},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5600865483283997},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5219787359237671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35682588815689087},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10681214928627014},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09716036915779114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7033724188804626},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6899077892303467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6866728067398071},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5867984890937805},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5600865483283997},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5219787359237671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35682588815689087},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10681214928627014},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09716036915779114},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G3457189404","display_name":null,"funder_award_id":"2022ZD0118002","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5036096801","display_name":null,"funder_award_id":"2023119","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G6143720773","display_name":null,"funder_award_id":"62106255","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6794249700","display_name":null,"funder_award_id":"ISCASZD-202401,ISCAS-JCMS-202306","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1973085892","https://openalex.org/W2022683396","https://openalex.org/W2091380405","https://openalex.org/W2108432853","https://openalex.org/W2151936436","https://openalex.org/W2990712847","https://openalex.org/W3036136559","https://openalex.org/W3037845634","https://openalex.org/W3043821616","https://openalex.org/W3091860345","https://openalex.org/W3134992347","https://openalex.org/W3191765704","https://openalex.org/W3197811449","https://openalex.org/W3198239978","https://openalex.org/W3198524283","https://openalex.org/W3201359772","https://openalex.org/W3203140070","https://openalex.org/W4224931267","https://openalex.org/W4280517984","https://openalex.org/W4285335793","https://openalex.org/W4297267083","https://openalex.org/W4297841418","https://openalex.org/W4297841864","https://openalex.org/W4301185282","https://openalex.org/W4368360280","https://openalex.org/W4372259808","https://openalex.org/W4372260492","https://openalex.org/W4372338196","https://openalex.org/W4372346506","https://openalex.org/W4372346992","https://openalex.org/W4375869247","https://openalex.org/W4375869449","https://openalex.org/W4385822442","https://openalex.org/W4385822978","https://openalex.org/W4385822990","https://openalex.org/W4385823081","https://openalex.org/W4385823120","https://openalex.org/W4385823241","https://openalex.org/W4390938216","https://openalex.org/W4392903599","https://openalex.org/W4392903796","https://openalex.org/W4392909911","https://openalex.org/W4401609199","https://openalex.org/W6780218876","https://openalex.org/W6810168380","https://openalex.org/W6862568103","https://openalex.org/W6866580884"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Dysarthria,":[0],"a":[1,71,125,138],"speech":[2,12],"disorder":[3],"resulting":[4],"from":[5],"neurological":[6],"conditions,":[7],"presents":[8],"significant":[9],"obstacles":[10],"to":[11,23,74],"intelligibility":[13],"and":[14,27,39,66,92,109,167],"daily":[15],"communication.":[16],"Automatic":[17],"dysarthria":[18,76,157],"assessment":[19,56],"has":[20],"the":[21,44,54,80,119,132,147,160,163],"capability":[22],"provide":[24],"low-cost":[25],"diagnosis":[26,166],"treatment":[28],"assistant":[29],"support":[30],"for":[31,53,155,162],"such":[32],"diseases":[33],"as":[34],"Parkinson's":[35],"disease,":[36,38],"Alzheimer's":[37],"stroke.":[40],"This":[41,144],"study":[42,145],"investigates":[43],"efficacy":[45],"of":[46,57,129,142,150,165],"cross-modality":[47],"feature":[48,110],"fusion":[49,108,111,122,135],"using":[50],"audio-visual":[51],"data":[52],"automatic":[55],"dysarthric":[58],"speech.":[59],"Leveraging":[60],"advanced":[61],"self-supervised":[62,152],"learning":[63,153],"models,":[64],"AV-HuBERT":[65],"Wav2Vec":[67],"2.0,":[68],"we":[69],"develop":[70],"multimodal":[72,156],"system":[73,98,123,136],"enhance":[75],"severity":[77],"classification.":[78],"Utilizing":[79],"Mandarin":[81],"Subacute":[82],"Stroke":[83],"Dysarthria":[84],"Multimodal":[85],"(MSDM)":[86],"dataset,":[87],"which":[88],"includes":[89],"synchronized":[90],"audio":[91],"lip":[93],"movement":[94],"video":[95],"recordings,":[96],"our":[97,106],"achieves":[99],"promising":[100],"performance.":[101],"Experimental":[102],"results":[103],"demonstrate":[104],"that":[105],"back-end":[107,121],"approaches":[112],"both":[113],"outperform":[114],"traditional":[115],"single-modality":[116],"methods,":[117],"with":[118],"best":[120,133],"achieving":[124,137],"speaker-level":[126,139],"F1":[127,140],"score":[128,141],"0.841":[130],"while":[131],"feature-level":[134],"0.772.":[143],"marks":[146],"first":[148],"application":[149],"pre-trained":[151],"models":[154],"assessment,":[158],"highlighting":[159],"potential":[161],"assistance":[164],"treatment.":[168]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
