{"id":"https://openalex.org/W4410297768","doi":"https://doi.org/10.1109/hri61500.2025.10973958","title":"Applying General Turn-Taking Models to Conversational Human-Robot Interaction","display_name":"Applying General Turn-Taking Models to Conversational Human-Robot Interaction","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410297768","doi":"https://doi.org/10.1109/hri61500.2025.10973958"},"language":"en","primary_location":{"id":"doi:10.1109/hri61500.2025.10973958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10973958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","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/A5091225228","display_name":"Gabriel Skantze","orcid":"https://orcid.org/0000-0002-8579-1790"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Gabriel Skantze","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091756638","display_name":"Bahar Irfan","orcid":"https://orcid.org/0000-0002-7983-079X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Bahar Irfan","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091225228"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":48.1909,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.99802112,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"859","last_page":"868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.982699990272522,"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":0.982699990272522,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9537000060081482,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T12128","display_name":"AI in Service Interactions","score":0.9513999819755554,"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/turn-taking","display_name":"Turn-taking","score":0.8187234997749329},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.6884336471557617},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6412631273269653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6371194124221802},{"id":"https://openalex.org/keywords/turn","display_name":"Turn (biochemistry)","score":0.5691575407981873},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5293363332748413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2867739498615265},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.20869752764701843},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.18068450689315796},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14168938994407654},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06186652183532715}],"concepts":[{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.8187234997749329},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.6884336471557617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6412631273269653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6371194124221802},{"id":"https://openalex.org/C85641259","wikidata":"https://www.wikidata.org/wiki/Q290042","display_name":"Turn (biochemistry)","level":2,"score":0.5691575407981873},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5293363332748413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2867739498615265},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.20869752764701843},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.18068450689315796},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14168938994407654},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06186652183532715},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hri61500.2025.10973958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10973958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2900127165","https://openalex.org/W320957374","https://openalex.org/W2379107843","https://openalex.org/W3120641923","https://openalex.org/W2909654650","https://openalex.org/W3161619631","https://openalex.org/W4242512034","https://openalex.org/W3003178987","https://openalex.org/W4376475259","https://openalex.org/W2804368879"],"abstract_inverted_index":{"Turn-taking":[0],"is":[1],"a":[2,79,97,101,113,119],"fundamental":[3],"aspect":[4],"of":[5,34],"conversation,":[6],"but":[7],"current":[8],"Human-Robot":[9],"Interaction":[10],"(HRI)":[11],"systems":[12],"often":[13],"rely":[14],"on":[15,55],"simplistic,":[16],"silence-based":[17],"models,":[18,37],"leading":[19],"to":[20,45,76],"unnatural":[21],"pauses":[22],"and":[23,40,87,137,143],"interruptions.":[24,90,144],"This":[25],"paper":[26],"investigates,":[27],"for":[28,70,123],"the":[29,32,93,106,134],"first":[30],"time,":[31],"application":[33],"general":[35],"turn-taking":[36],"specifically":[38],"TurnGPT":[39],"Voice":[41],"Activity":[42],"Projection":[43],"(VAP),":[44],"improve":[46],"conversational":[47,114],"dynamics":[48],"in":[49,74,96,112,116],"HRI.":[50],"These":[51],"models":[52,73],"are":[53],"trained":[54],"human-human":[56],"dialogue":[57],"data":[58],"using":[59,71,105],"self-supervised":[60],"learning":[61],"objectives,":[62],"without":[63],"requiring":[64],"domain-specific":[65],"fine-tuning.":[66],"We":[67,91],"propose":[68],"methods":[69],"these":[72],"tandem":[75],"predict":[77],"when":[78],"robot":[80,108],"should":[81],"begin":[82],"preparing":[83],"responses,":[84],"take":[85],"turns,":[86],"handle":[88],"potential":[89],"evaluated":[92],"proposed":[94,135],"system":[95],"within-subject":[98],"study":[99],"against":[100],"traditional":[102],"baseline":[103],"system,":[104,136],"Furhat":[107],"with":[109,118],"39":[110],"adults":[111],"setting,":[115],"combination":[117],"large":[120],"language":[121],"model":[122],"autonomous":[124],"response":[125,141],"generation.":[126],"The":[127],"results":[128],"show":[129],"that":[130],"participants":[131],"significantly":[132,139],"prefer":[133],"it":[138],"reduces":[140],"delays":[142]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":10}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}