{"id":"https://openalex.org/W7148399660","doi":"https://doi.org/10.1109/asru65441.2025.11433839","title":"CAVIARES: Corpus for Audio-Visual Expressive Voice Agent","display_name":"CAVIARES: Corpus for Audio-Visual Expressive Voice Agent","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148399660","doi":"https://doi.org/10.1109/asru65441.2025.11433839"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11433839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"display_name":"Jinsheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jinsheng Chen","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132793760","display_name":"Yuki Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132812838","display_name":"Dong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dong Yang","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059290592","display_name":"Naoko Tanji","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoko Tanji","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024608998","display_name":"Hironori Doi","orcid":null},"institutions":[{"id":"https://openalex.org/I149530613","display_name":"Lynn University","ror":"https://ror.org/04nqv0v23","country_code":"US","type":"education","lineage":["https://openalex.org/I149530613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hironori Doi","raw_affiliation_strings":["LY Corp.,Japan"],"affiliations":[{"raw_affiliation_string":"LY Corp.,Japan","institution_ids":["https://openalex.org/I149530613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065423721","display_name":"Byeongseon Park","orcid":"https://orcid.org/0000-0002-7419-7999"},"institutions":[{"id":"https://openalex.org/I149530613","display_name":"Lynn University","ror":"https://ror.org/04nqv0v23","country_code":"US","type":"education","lineage":["https://openalex.org/I149530613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byeongseon Park","raw_affiliation_strings":["LY Corp.,Japan"],"affiliations":[{"raw_affiliation_string":"LY Corp.,Japan","institution_ids":["https://openalex.org/I149530613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132754325","display_name":"Yuma Shirahata","orcid":null},"institutions":[{"id":"https://openalex.org/I149530613","display_name":"Lynn University","ror":"https://ror.org/04nqv0v23","country_code":"US","type":"education","lineage":["https://openalex.org/I149530613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuma Shirahata","raw_affiliation_strings":["LY Corp.,Japan"],"affiliations":[{"raw_affiliation_string":"LY Corp.,Japan","institution_ids":["https://openalex.org/I149530613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132778017","display_name":"Kentaro Tachibana","orcid":null},"institutions":[{"id":"https://openalex.org/I149530613","display_name":"Lynn University","ror":"https://ror.org/04nqv0v23","country_code":"US","type":"education","lineage":["https://openalex.org/I149530613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kentaro Tachibana","raw_affiliation_strings":["LY Corp.,Japan"],"affiliations":[{"raw_affiliation_string":"LY Corp.,Japan","institution_ids":["https://openalex.org/I149530613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132825754","display_name":"Hiroshi Saruwatari","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86692989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.22939999401569366,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.22939999401569366,"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/T12031","display_name":"Speech and dialogue systems","score":0.18569999933242798,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.10949999839067459,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28519999980926514},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.25110000371932983},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2409999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49219998717308044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27300000190734863},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2409999966621399}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11433839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2037357509","https://openalex.org/W2471520273","https://openalex.org/W2514026573","https://openalex.org/W2519648275","https://openalex.org/W2726515241","https://openalex.org/W2799930024","https://openalex.org/W2964243274","https://openalex.org/W3015383493","https://openalex.org/W3081492798","https://openalex.org/W3081800019","https://openalex.org/W3089177030","https://openalex.org/W3099284785","https://openalex.org/W4221163454","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823169","https://openalex.org/W4386066256","https://openalex.org/W4386072021"],"related_works":[],"abstract_inverted_index":{"High-quality":[0],"audio-visual":[1,35],"corpora":[2,16],"are":[3],"essential":[4],"for":[5,68,96],"building":[6],"voice":[7],"agents":[8],"capable":[9],"of":[10,22,40,53,65,84,89],"natural":[11],"human-machine":[12],"communication,":[13],"but":[14],"existing":[15],"commonly":[17],"contain":[18],"a":[19,33,45,62],"limited":[20],"amount":[21],"data":[23],"per":[24],"speaker,":[25],"making":[26],"personalized":[27],"modeling":[28,71],"difficult.":[29],"We":[30],"present":[31],"CAVIARES,":[32],"new":[34],"corpus":[36,90],"comprising":[37],"9.5":[38],"hours":[39],"expressive":[41,59],"speech":[42],"recorded":[43],"by":[44],"single":[46],"professional":[47],"Japanese":[48],"female":[49],"speaker.":[50],"CAVIARES":[51,85,92],"consists":[52],"two":[54],"subsets:":[55],"acted":[56],"dialogue":[57],"and":[58,72,86],"reading,":[60],"providing":[61],"diverse":[63],"range":[64],"speaking":[66],"styles":[67],"speech-to-facial":[69],"motion":[70],"multimodal":[73],"learning":[74],"tasks.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"describe":[80],"the":[81,87],"construction":[82],"process":[83],"results":[88],"analysis.":[91],"will":[93],"be":[94],"released":[95],"research":[97],"purposes":[98],"only.":[99]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}
