{"id":"https://openalex.org/W4411237617","doi":"https://doi.org/10.1145/3708319.3733662","title":"Towards a Structured Multimodal Speech-Image Coordination","display_name":"Towards a Structured Multimodal Speech-Image Coordination","publication_year":2025,"publication_date":"2025-06-12","ids":{"openalex":"https://openalex.org/W4411237617","doi":"https://doi.org/10.1145/3708319.3733662"},"language":"en","primary_location":{"id":"doi:10.1145/3708319.3733662","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733662","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733662","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733662","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044203797","display_name":"Massimo Donini","orcid":"https://orcid.org/0009-0008-7123-2921"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Donini","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0008-7123-2921","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118361388","display_name":"Michael Oliverio","orcid":null},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michael Oliverio","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0007-3448-2377","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114262999","display_name":"Pier Felice Balestrucci","orcid":"https://orcid.org/0009-0001-2161-2263"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pier Felice Balestrucci","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0001-2161-2263","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043355817","display_name":"Luca Anselma","orcid":"https://orcid.org/0000-0003-2292-6480"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Anselma","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2292-6480","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021163942","display_name":"Cristina Gena","orcid":"https://orcid.org/0000-0003-0049-6213"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristina Gena","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0049-6213","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013143796","display_name":"Alessandro Mazzei","orcid":"https://orcid.org/0000-0003-3072-0108"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Mazzei","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3072-0108","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000813248","display_name":"Matteo Nazzario","orcid":"https://orcid.org/0009-0005-1975-6769"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Nazzario","raw_affiliation_strings":["Intesa SanPaolo Innovation Center, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0005-1975-6769","affiliations":[{"raw_affiliation_string":"Intesa SanPaolo Innovation Center, Turin, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006450114","display_name":"Irene Borgini","orcid":"https://orcid.org/0009-0007-9748-648X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irene Borgini","raw_affiliation_strings":["Intesa SanPaolo Innovation Center, Turin, Italy"],"raw_orcid":"https://orcid.org/0009-0007-9748-648X","affiliations":[{"raw_affiliation_string":"Intesa SanPaolo Innovation Center, Turin, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8413312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9703999757766724,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9688000082969666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696235537528992},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5434575080871582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4149787425994873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051540493965149},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37703901529312134},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.339803010225296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696235537528992},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5434575080871582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4149787425994873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051540493965149},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37703901529312134},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.339803010225296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3708319.3733662","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733662","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733662","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3708319.3733662","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733662","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733662","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411237617.pdf","grobid_xml":"https://content.openalex.org/works/W4411237617.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1990080833","https://openalex.org/W2028660085","https://openalex.org/W2053459428","https://openalex.org/W2082606349","https://openalex.org/W3037856681","https://openalex.org/W3094833381","https://openalex.org/W3174781398","https://openalex.org/W4239187549","https://openalex.org/W4361204578","https://openalex.org/W4377227441","https://openalex.org/W4392658223","https://openalex.org/W4394994605","https://openalex.org/W4400106318","https://openalex.org/W4407624561","https://openalex.org/W4409735401"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,110],"novel":[4],"approach":[5,106],"to":[6,59,78,108,123],"the":[7,10,46,63,89,120,124],"use":[8],"of":[9,65],"humanoid":[11],"robot":[12,47,57],"Pepper":[13],"in":[14,27,42],"educational":[15],"contexts,":[16],"focusing":[17],"on":[18,54],"dialogic":[19],"and":[20,29,70,87,99,114,127],"multimodal":[21],"interaction":[22],"for":[23,103],"teaching":[24],"abstract":[25],"concepts":[26],"mathematics":[28],"physics.Unlike":[30],"traditional":[31],"lecture-based":[32],"models,":[33],"our":[34],"system":[35,90],"supports":[36],"learner-centered":[37],"lessons":[38],"where":[39],"students":[40],"engage":[41],"spontaneous":[43],"dialogue":[44],"with":[45,50],"while":[48],"interacting":[49],"visual":[51,72,93],"content":[52,122],"displayed":[53],"its":[55],"tablet.The":[56],"responds":[58],"user":[60],"questions":[61],"through":[62],"coordination":[64],"speech,":[66],"synchronized":[67],"textual":[68],"output,":[69],"dynamic":[71],"cues,":[73],"such":[74,95],"as":[75,96],"real-time":[76],"modifications":[77],"vectorial":[79],"images":[80],"that":[81],"highlight":[82],"relevant":[83],"elements.To":[84],"promote":[85],"accessibility":[86],"engagement,":[88],"includes":[91],"customizable":[92],"features":[94],"color":[97],"schemes":[98],"adjustable":[100],"font":[101],"settings":[102],"visual-impaired":[104],"users.This":[105],"aims":[107],"foster":[109],"more":[111],"inclusive,":[112],"personalized,":[113],"interactive":[115],"learning":[116],"experience":[117],"by":[118],"adapting":[119],"lesson":[121],"learner's":[125],"interests":[126],"inquiries.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
