{"id":"https://openalex.org/W4415821687","doi":"https://doi.org/10.1109/ro-man63969.2025.11217726","title":"Dynamic Prompting Improves Turn-taking in Embodied Spoken Dialogue Systems","display_name":"Dynamic Prompting Improves Turn-taking in Embodied Spoken Dialogue Systems","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415821687","doi":"https://doi.org/10.1109/ro-man63969.2025.11217726"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101607505","display_name":"Yifan Shen","orcid":"https://orcid.org/0009-0006-9205-3266"},"institutions":[{"id":"https://openalex.org/I4210133369","display_name":"Decision Sciences (United States)","ror":"https://ror.org/03gcvf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133369"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Yifan Shen","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)","institution_ids":["https://openalex.org/I4210133369","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053220954","display_name":"Dingdong Liu","orcid":"https://orcid.org/0000-0003-0985-0979"},"institutions":[{"id":"https://openalex.org/I4210133369","display_name":"Decision Sciences (United States)","ror":"https://ror.org/03gcvf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133369"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Dingdong Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)","institution_ids":["https://openalex.org/I4210133369","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093130804","display_name":"Xiaoyu Mo","orcid":"https://orcid.org/0000-0001-6009-6487"},"institutions":[{"id":"https://openalex.org/I4210133369","display_name":"Decision Sciences (United States)","ror":"https://ror.org/03gcvf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133369"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Mo","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)","institution_ids":["https://openalex.org/I4210133369","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048627515","display_name":"Fugee Tsung","orcid":"https://orcid.org/0000-0002-0575-8254"},"institutions":[{"id":"https://openalex.org/I4210133369","display_name":"Decision Sciences (United States)","ror":"https://ror.org/03gcvf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133369"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Fugee Tsung","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)","institution_ids":["https://openalex.org/I4210133369","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026376235","display_name":"Xiaojuan Ma","orcid":"https://orcid.org/0000-0002-9847-7784"},"institutions":[{"id":"https://openalex.org/I4210133369","display_name":"Decision Sciences (United States)","ror":"https://ror.org/03gcvf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133369"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Xiaojuan Ma","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)","institution_ids":["https://openalex.org/I4210133369","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068036711","display_name":"Bertram E. Shi","orcid":"https://orcid.org/0000-0001-9167-7495"},"institutions":[{"id":"https://openalex.org/I4210133369","display_name":"Decision Sciences (United States)","ror":"https://ror.org/03gcvf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133369"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Bertram E. Shi","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)","institution_ids":["https://openalex.org/I4210133369","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"692","last_page":"699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.4997999966144562,"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":0.4997999966144562,"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":0.3815000057220459,"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/T11431","display_name":"Action Observation and Synchronization","score":0.02810000069439411,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7717000246047974},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7045000195503235},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6258999705314636},{"id":"https://openalex.org/keywords/interrupt","display_name":"Interrupt","score":0.5931000113487244},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.5126000046730042},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4715999960899353},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.4677000045776367},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4530999958515167}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7717000246047974},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7045000195503235},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6258999705314636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5990999937057495},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.5931000113487244},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.5126000046730042},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5116999745368958},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4715999960899353},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32589998841285706},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29919999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168056","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168056","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1964725106","https://openalex.org/W2067097374","https://openalex.org/W2067348796","https://openalex.org/W2081703679","https://openalex.org/W2161296357","https://openalex.org/W2202997319","https://openalex.org/W2293392332","https://openalex.org/W2502840125","https://openalex.org/W2765447327","https://openalex.org/W3000596306","https://openalex.org/W3009894005","https://openalex.org/W3094393093","https://openalex.org/W3112188842","https://openalex.org/W3169860338","https://openalex.org/W4282030117","https://openalex.org/W4297841817","https://openalex.org/W4301357669","https://openalex.org/W4385992525","https://openalex.org/W4391213551","https://openalex.org/W4403918885","https://openalex.org/W4403918898","https://openalex.org/W4410297768","https://openalex.org/W4412023051","https://openalex.org/W4412945230"],"related_works":[],"abstract_inverted_index":{"The":[0,23,125],"ability":[1],"to":[2,26,46,53,71,111,144,148,187,193,199,203],"coordinate":[3,60,93],"turn":[4],"taking":[5],"during":[6],"spoken":[7,14],"dialogue":[8,15],"is":[9],"crucial":[10],"for":[11],"an":[12,103,112,159],"embodied":[13],"system":[16,143],"(SDS),":[17],"e.g.,":[18],"in":[19,29,206],"a":[20,162,166],"humanoid":[21,163],"robot.":[22],"SDS":[24,44,67,104],"needs":[25,45],"model":[27,188],"transitions":[28,62,74,95,190],"the":[30,43,51,54,121,131,136,142,149,185],"conversational":[31,122],"floor,":[32],"which":[33],"describes":[34],"each":[35],"party\u2019s":[36],"stance":[37,147],"(either":[38],"speaking":[39],"or":[40],"listening).":[41],"Further,":[42],"signal":[47,145],"its":[48,109,118,146],"perception":[49,119],"of":[50,120],"floor":[52,61,73,94,123,138,189],"human,":[55,150],"so":[56],"that":[57,106],"they":[58],"can":[59],"and":[63,80,154,198],"resolve":[64],"conflicts.":[65],"Conventional":[66],"employ":[68],"standalone":[69],"modules":[70],"control":[72],"but":[75,90,134],"do":[76,91],"not":[77,92,129],"produce":[78],"timely":[79],"appropriate":[81,196],"responses.":[82],"Recent":[83],"end-to-end":[84,113],"audio":[85,114,132],"LLMs":[86],"generate":[87,194],"responses":[88],"quickly,":[89],"as":[96],"accurately.":[97],"In":[98],"this":[99],"work,":[100],"we":[101],"propose":[102],"architecture":[105],"dynamically":[107],"adjusts":[108],"prompts":[110],"LLM":[115,126,186],"based":[116],"upon":[117],"state.":[124,139],"output":[127],"determines":[128],"only":[130],"output,":[133],"also":[135],"perceived":[137],"This":[140],"enables":[141,184],"both":[151],"when":[152,155],"listening":[153],"speaking.":[156],"We":[157],"conducted":[158],"experiment":[160],"where":[161],"robot":[164],"administered":[165],"semi-structured":[167],"interview":[168],"with":[169,176],"human":[170],"subjects.":[171],"Results":[172],"show":[173],"that,":[174],"compared":[175],"baseline":[177],"systems":[178],"using":[179],"static":[180],"prompts,":[181],"dynamic":[182],"prompting":[183],"more":[191,195],"accurately,":[192],"signalling,":[197],"interrupt":[200],"less,":[201],"leading":[202],"smoother":[204],"turn-taking":[205],"dialogue.":[207]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-03T00:00:00"}