{"id":"https://openalex.org/W4404284944","doi":"https://doi.org/10.1587/transinf.2024hcp0002","title":"Multimodal Voice Activity Projection for Turn-Taking and Effects on Speaker Adaptation","display_name":"Multimodal Voice Activity Projection for Turn-Taking and Effects on Speaker Adaptation","publication_year":2024,"publication_date":"2024-11-12","ids":{"openalex":"https://openalex.org/W4404284944","doi":"https://doi.org/10.1587/transinf.2024hcp0002"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024hcp0002","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024hcp0002","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/6/E108.D_2024HCP0002/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/6/E108.D_2024HCP0002/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kazuyo ONISHI","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyo ONISHI","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043099974","display_name":"Hiroki Tanaka","orcid":"https://orcid.org/0000-0002-0548-6252"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki TANAKA","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011428539","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-7978-0705"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi NAKAMURA","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":2.0949,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89470921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"E108.D","issue":"6","first_page":"445","last_page":"453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10021","display_name":"EFL/ESL Teaching and Learning","score":0.8666999936103821,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10021","display_name":"EFL/ESL Teaching and Learning","score":0.8666999936103821,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.8525999784469604,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13795","display_name":"Language, Communication, and Linguistic Studies","score":0.8151000142097473,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8321144580841064},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7467900514602661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6184825301170349},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.554508626461029},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.43132054805755615},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3546849489212036},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.17092016339302063},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11345067620277405},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07708984613418579},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.062290698289871216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321144580841064},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7467900514602661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6184825301170349},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.554508626461029},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.43132054805755615},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3546849489212036},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.17092016339302063},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11345067620277405},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07708984613418579},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.062290698289871216},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024hcp0002","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024hcp0002","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/6/E108.D_2024HCP0002/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024hcp0002","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024hcp0002","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E108.D/6/E108.D_2024HCP0002/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1909282687","display_name":"Building Rapport in Social Communication Training Systems for Autism Spectrum Disorders","funder_award_id":"22K12151","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2363020693","display_name":"A Study on Multi-modal Automatic Simultaneous Interpretation System and Evaluation Method","funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404284944.pdf","grobid_xml":"https://content.openalex.org/works/W4404284944.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W83250750","https://openalex.org/W83540058","https://openalex.org/W1508665521","https://openalex.org/W1605330792","https://openalex.org/W1608166496","https://openalex.org/W1964725106","https://openalex.org/W1967691260","https://openalex.org/W2007889078","https://openalex.org/W2063643001","https://openalex.org/W2100844198","https://openalex.org/W2141061570","https://openalex.org/W2162634167","https://openalex.org/W2166637769","https://openalex.org/W2492441051","https://openalex.org/W2515585303","https://openalex.org/W2747602812","https://openalex.org/W2752741953","https://openalex.org/W2755291975","https://openalex.org/W2786387151","https://openalex.org/W2805479865","https://openalex.org/W2807126412","https://openalex.org/W2842511635","https://openalex.org/W2888997666","https://openalex.org/W2914243039","https://openalex.org/W2962730651","https://openalex.org/W2970971581","https://openalex.org/W2973172454","https://openalex.org/W2980823180","https://openalex.org/W3112188842","https://openalex.org/W3134485584","https://openalex.org/W3196984997","https://openalex.org/W3199141871","https://openalex.org/W4251847946","https://openalex.org/W4297841632","https://openalex.org/W4297841817","https://openalex.org/W4306752156","https://openalex.org/W4323270439","https://openalex.org/W4387322685","https://openalex.org/W4389009518","https://openalex.org/W4389282358","https://openalex.org/W4389518657"],"related_works":["https://openalex.org/W2150330603","https://openalex.org/W2997567050","https://openalex.org/W2605987115","https://openalex.org/W2337323018","https://openalex.org/W4220795486","https://openalex.org/W2900127165","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W2379107843","https://openalex.org/W1526712007"],"abstract_inverted_index":{"The":[0,100,117],"prediction":[1],"of":[2,27,43,50,59,74,87,105,131],"utterances":[3],"in":[4,67,72,97],"two-party":[5],"conversations":[6],"is":[7],"a":[8,28,129],"crucial":[9],"technology":[10],"for":[11,123],"realizing":[12],"natural":[13],"turn-taking":[14,33,108],"between":[15],"humans":[16],"and":[17,79,133],"virtual":[18,98],"agents.":[19,99],"Recently,":[20],"Voice":[21],"Activity":[22],"Projection":[23],"(VAP)":[24],"models,":[25,70],"capable":[26],"unified":[29],"approach":[30],"to":[31,46,63,112],"various":[32],"events,":[34],"have":[35],"gained":[36],"attention.":[37],"This":[38],"study":[39,118],"investigates":[40],"the":[41,48,57,68,85,103,110,113,121],"incorporation":[42],"non-verbal":[44,60,134],"features":[45,61],"enhance":[47],"performance":[49,66,86,125],"VAP":[51,69,88],"models.":[52],"Our":[53],"results":[54],"indicate":[55],"that":[56],"integration":[58],"leads":[62],"significantly":[64],"better":[65],"particularly":[71],"aspects":[73],"turn-shift":[75],"prediction,":[76,78],"overlap":[77],"backchannel":[80],"prediction.":[81],"Moreover,":[82],"we":[83],"explored":[84],"models":[89],"using":[90],"only":[91],"single-speaker":[92],"features,":[93],"targeting":[94],"their":[95],"implementation":[96],"findings":[101],"demonstrate":[102],"feasibility":[104],"adequately":[106],"predicting":[107],"from":[109],"user":[111],"spoken":[114],"dialogue":[115],"system.":[116],"also":[119],"outlines":[120],"potential":[122],"further":[124],"enhancement":[126],"by":[127],"integrating":[128],"variety":[130],"language":[132],"features.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}