{"id":"https://openalex.org/W7134936681","doi":"https://doi.org/10.9781/ijimai.2026.2215","title":"Improving Aphasic Communication Using Multimodal AI Systems","display_name":"Improving Aphasic Communication Using Multimodal AI Systems","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134936681","doi":"https://doi.org/10.9781/ijimai.2026.2215"},"language":"en","primary_location":{"id":"doi:10.9781/ijimai.2026.2215","is_oa":true,"landing_page_url":"https://doi.org/10.9781/ijimai.2026.2215","pdf_url":"https://www.ijimai.org/index.php/ijimai/article/download/2215/3719","source":{"id":"https://openalex.org/S2738898797","display_name":"International Journal of Interactive Multimedia and Artificial Intelligence","issn_l":"1989-1660","issn":["1989-1660"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321767","host_organization_name":"International University of La Rioja","host_organization_lineage":["https://openalex.org/P4310321767"],"host_organization_lineage_names":["International University of La Rioja"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.ijimai.org/index.php/ijimai/article/download/2215/3719","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092989962","display_name":"Isabel Ferri-Molla","orcid":"https://orcid.org/0009-0008-3608-9891"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Isabel Ferri-Molla","raw_affiliation_strings":["Polytechnic University of Valencia"],"raw_orcid":"https://orcid.org/0009-0008-3608-9891","affiliations":[{"raw_affiliation_string":"Polytechnic University of Valencia","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126414554","display_name":"Jordi Linares-Pellicer","orcid":null},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Linares-Pellicer","raw_affiliation_strings":["Polytechnic University of Valencia"],"raw_orcid":"https://orcid.org/0000-0002-3315-1716","affiliations":[{"raw_affiliation_string":"Polytechnic University of Valencia","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128758928","display_name":"Juan Izquierdo-Domenech","orcid":null},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Izquierdo-Domenech","raw_affiliation_strings":["Polytechnic University of Valencia"],"raw_orcid":"https://orcid.org/0000-0003-0076-7001","affiliations":[{"raw_affiliation_string":"Polytechnic University of Valencia","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25513031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"7","first_page":"67","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.53329998254776,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.53329998254776,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12207","display_name":"Assistive Technology in Communication and Mobility","score":0.13230000436306,"subfield":{"id":"https://openalex.org/subfields/3609","display_name":"Occupational Therapy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.08669999986886978,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.6261000037193298},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5396000146865845},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4578999876976013},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40049999952316284},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3181000053882599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.909600019454956},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5885000228881836},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4749999940395355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.9781/ijimai.2026.2215","is_oa":true,"landing_page_url":"https://doi.org/10.9781/ijimai.2026.2215","pdf_url":"https://www.ijimai.org/index.php/ijimai/article/download/2215/3719","source":{"id":"https://openalex.org/S2738898797","display_name":"International Journal of Interactive Multimedia and Artificial Intelligence","issn_l":"1989-1660","issn":["1989-1660"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321767","host_organization_name":"International University of La Rioja","host_organization_lineage":["https://openalex.org/P4310321767"],"host_organization_lineage_names":["International University of La Rioja"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0323aa6ee80e48b98d90c64d8067e063","is_oa":true,"landing_page_url":"https://doaj.org/article/0323aa6ee80e48b98d90c64d8067e063","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.9781/ijimai.2026.2215","is_oa":true,"landing_page_url":"https://doi.org/10.9781/ijimai.2026.2215","pdf_url":"https://www.ijimai.org/index.php/ijimai/article/download/2215/3719","source":{"id":"https://openalex.org/S2738898797","display_name":"International Journal of Interactive Multimedia and Artificial Intelligence","issn_l":"1989-1660","issn":["1989-1660"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321767","host_organization_name":"International University of La Rioja","host_organization_lineage":["https://openalex.org/P4310321767"],"host_organization_lineage_names":["International University of La Rioja"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7810974717140198,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G852292892","display_name":null,"funder_award_id":"CI-PROM/2021/077","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"}],"funders":[{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134936681.pdf","grobid_xml":"https://content.openalex.org/works/W7134936681.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aphasia,":[0],"often":[1],"resulting":[2],"from":[3,81,106,115],"brain":[4],"injuries,":[5],"significantly":[6],"impairs":[7],"individuals\u2019":[8],"language":[9,188],"abilities,":[10],"creating":[11],"substantial":[12],"challenges":[13],"for":[14,33],"verbal":[15],"communication.":[16],"Existing":[17],"assistive":[18],"technologies":[19],"frequently":[20],"fall":[21],"short":[22],"in":[23,90,110,119],"addressing":[24],"these":[25],"specialised":[26],"communication":[27],"needs,":[28],"underscoring":[29],"the":[30,64,82,131,134,137,152,169,175],"urgent":[31],"demand":[32],"adaptive,":[34],"intelligent":[35],"support":[36],"systems.":[37],"This":[38],"research":[39],"proposes":[40],"a":[41,55,87,111,120,144,165],"dual":[42],"approach:":[43],"an":[44],"Automatic":[45],"Speech":[46],"Recognition":[47],"(ASR)":[48],"module":[49],"fine-tuned":[50,72],"on":[51,79],"aphasic":[52],"speech,":[53],"and":[54,76,114],"multimodal":[56,138],"component":[57,139],"that":[58,182],"integrates":[59],"visual":[60,185],"context":[61],"to":[62,108,117,130,142,150,172],"infer":[63],"speaker\u2019s":[65,153],"intended":[66],"meaning.":[67],"The":[68,179],"ASR":[69,99,132],"system":[70],"leverages":[71],"versions":[73],"of":[74,136],"Whisper":[75],"Wav2Vec":[77],"2.0":[78],"data":[80],"AphasiaBank":[83],"corpus.":[84],"Results":[85],"show":[86],"notable":[88],"reduction":[89],"Word":[91],"Error":[92],"Rate":[93],"(WER)":[94],"when":[95],"comparing":[96],"base":[97],"pre-trained":[98],"models":[100],"with":[101,187],"their":[102],"finetuned":[103],"versions,":[104],"decreasing":[105],"70.36%":[107],"31.53%":[109],"contextindependent":[112],"setting,":[113],"61.25%":[116],"35.60%":[118],"speaker-independent":[121],"evaluation,":[122],"demonstrating":[123],"robustness":[124],"across":[125],"different":[126],"scenarios.":[127],"In":[128],"contrast":[129],"module,":[133],"goal":[135],"is":[140],"not":[141],"produce":[143],"literal":[145],"word-by-word":[146],"transcription,":[147],"but":[148],"rather":[149],"reconstruct":[151],"communicative":[154,194],"intent":[155,195],"using":[156],"contextual":[157],"information.":[158],"To":[159],"evaluate":[160],"this":[161],"capability,":[162],"we":[163],"conducted":[164],"human":[166],"study":[167],"assessing":[168],"system\u2019s":[170],"ability":[171],"interpret":[173],"what":[174],"speaker":[176],"truly":[177],"meant.":[178],"results":[180],"confirmed":[181],"outputs":[183],"combining":[184],"cues":[186],"model":[189],"reasoning":[190],"more":[191],"reliably":[192],"captured":[193],"than":[196],"audio-only":[197],"transcriptions.":[198]},"counts_by_year":[],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-03-12T00:00:00"}
