{"id":"https://openalex.org/W3210634018","doi":"https://doi.org/10.1145/3486580","title":"Do Prosody and Embodiment Influence the Perceived Naturalness of Conversational Agents\u2019 Speech?","display_name":"Do Prosody and Embodiment Influence the Perceived Naturalness of Conversational Agents\u2019 Speech?","publication_year":2021,"publication_date":"2021-10-28","ids":{"openalex":"https://openalex.org/W3210634018","doi":"https://doi.org/10.1145/3486580","mag":"3210634018"},"language":"en","primary_location":{"id":"doi:10.1145/3486580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486580","pdf_url":null,"source":{"id":"https://openalex.org/S32453091","display_name":"ACM Transactions on Applied Perception","issn_l":"1544-3558","issn":["1544-3558","1544-3965"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Applied Perception","raw_type":"journal-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/A5075887658","display_name":"Jonathan Ehret","orcid":"https://orcid.org/0000-0001-6270-5119"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonathan Ehret","raw_affiliation_strings":["Visual Computing Institute, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Visual Computing Institute, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024589737","display_name":"Andrea B\u00f6nsch","orcid":"https://orcid.org/0000-0001-5077-3675"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrea B\u00f6nsch","raw_affiliation_strings":["Visual Computing Institute, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Visual Computing Institute, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091231198","display_name":"Lukas Asp\u00f6ck","orcid":"https://orcid.org/0000-0003-1248-8202"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Asp\u00f6ck","raw_affiliation_strings":["Institute for Hearing Technology and Acoustics, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Hearing Technology and Acoustics, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025120671","display_name":"Christine Tanja R\u00f6hr","orcid":"https://orcid.org/0000-0002-2911-8382"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christine T. R\u00f6hr","raw_affiliation_strings":["IfL Phonetik, University of Cologne, K\u00f6ln, Germany"],"affiliations":[{"raw_affiliation_string":"IfL Phonetik, University of Cologne, K\u00f6ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042326281","display_name":"Stefan Baumann","orcid":"https://orcid.org/0000-0002-7302-7103"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Baumann","raw_affiliation_strings":["IfL Phonetik, University of Cologne, K\u00f6ln, Germany"],"affiliations":[{"raw_affiliation_string":"IfL Phonetik, University of Cologne, K\u00f6ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051051406","display_name":"Martine Grice","orcid":"https://orcid.org/0000-0003-4973-4059"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martine Grice","raw_affiliation_strings":["IfL Phonetik, University of Cologne, K\u00f6ln, Germany"],"affiliations":[{"raw_affiliation_string":"IfL Phonetik, University of Cologne, K\u00f6ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074176667","display_name":"Janina Fels","orcid":"https://orcid.org/0000-0002-8694-7750"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Janina Fels","raw_affiliation_strings":["Institute for Hearing Technology and Acoustics, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Hearing Technology and Acoustics, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084069506","display_name":"Torsten Kuhlen","orcid":"https://orcid.org/0000-0003-2144-4367"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Torsten W. Kuhlen","raw_affiliation_strings":["Visual Computing Institute, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Visual Computing Institute, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5075887658"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.9598,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.88822152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"18","issue":"4","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991000294685364,"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":0.9991000294685364,"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/T12128","display_name":"AI in Service Interactions","score":0.9990000128746033,"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":0.9983000159263611,"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/prosody","display_name":"Prosody","score":0.9285962581634521},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8516218662261963},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6298350691795349},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.575907826423645},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5537301301956177},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.531292736530304},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49331727623939514},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4762282967567444},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4474669098854065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35271263122558594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34591442346572876},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34057772159576416},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.27937421202659607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13481661677360535}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9285962581634521},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8516218662261963},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6298350691795349},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.575907826423645},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5537301301956177},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.531292736530304},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49331727623939514},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4762282967567444},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4474669098854065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35271263122558594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34591442346572876},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34057772159576416},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27937421202659607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13481661677360535},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3486580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486580","pdf_url":null,"source":{"id":"https://openalex.org/S32453091","display_name":"ACM Transactions on Applied Perception","issn_l":"1544-3558","issn":["1544-3558","1544-3965"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Applied Perception","raw_type":"journal-article"},{"id":"pmh:oai:USBKOELN.ub.uni-koeln.de:57407","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400371","display_name":"K\u00f6lner Universit\u00e4ts PublikationsServer (Universit\u00e4t zu K\u00f6ln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210115942","host_organization_name":"Rhenish Institute for Environmental Research","host_organization_lineage":["https://openalex.org/I4210115942"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"doc-type:article"},{"id":"pmh:oai:publications.rwth-aachen.de:834813","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/834813","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18. Symposium on Applied Perception, SAP 2021, online, 2021-09-16 - 2021-09-17","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1542318638","https://openalex.org/W1561794768","https://openalex.org/W1951724000","https://openalex.org/W1965430868","https://openalex.org/W2001429584","https://openalex.org/W2013335684","https://openalex.org/W2021291367","https://openalex.org/W2024536104","https://openalex.org/W2080413246","https://openalex.org/W2094482505","https://openalex.org/W2125001590","https://openalex.org/W2129162329","https://openalex.org/W2139346079","https://openalex.org/W2149602309","https://openalex.org/W2169025255","https://openalex.org/W2398936787","https://openalex.org/W2415824434","https://openalex.org/W2486744320","https://openalex.org/W2526541248","https://openalex.org/W2538525110","https://openalex.org/W2550118691","https://openalex.org/W2582743722","https://openalex.org/W2603247401","https://openalex.org/W2603947633","https://openalex.org/W2626699878","https://openalex.org/W2730845691","https://openalex.org/W2789539594","https://openalex.org/W2807126412","https://openalex.org/W2896735034","https://openalex.org/W2900508683","https://openalex.org/W2914334074","https://openalex.org/W2920996501","https://openalex.org/W2946151048","https://openalex.org/W2951535830","https://openalex.org/W2964243274","https://openalex.org/W2972484110","https://openalex.org/W2982865155","https://openalex.org/W3046214721","https://openalex.org/W3111775938","https://openalex.org/W3149845000","https://openalex.org/W3159367349"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2071315723","https://openalex.org/W2075706796","https://openalex.org/W2507083698","https://openalex.org/W3100825170","https://openalex.org/W2465473908"],"abstract_inverted_index":{"For":[0],"conversational":[1],"agents\u2019":[2,214],"speech,":[3],"either":[4,118],"all":[5],"possible":[6],"sentences":[7],"have":[8],"to":[9,45,126,153,206,216,266],"be":[10,20,217],"prerecorded":[11],"by":[12,88,102,111,122,132,239,284],"voice":[13,211,246,253,275],"actors":[14],"or":[15,121,229],"the":[16,36,40,58,73,79,97,128,160,165,183,224,267,271,273,294,297,316,321,325,335],"required":[17],"utterances":[18],"can":[19],"synthesized.":[21],"While":[22],"synthesizing":[23],"speech":[24,115,176,199,215],"is":[25,177,203,221,227],"more":[26,180,188,257],"flexible":[27],"and":[28,62,76,106,164,197,232],"economic":[29],"in":[30,57,67,159,174,193,306,315,334],"production,":[31],"it":[32,202],"also":[33],"potentially":[34],"reduces":[35],"perceived":[37,74,178,186,218,303],"naturalness":[38,75,336],"of":[39,60,69,78,137,299,308,327,338],"agents":[41,184,329],"among":[42],"others":[43],"due":[44],"mistakes":[46],"at":[47],"various":[48],"linguistic":[49],"levels.":[50,168],"In":[51,288],"our":[52,290],"article,":[53],"we":[54,144,234],"are":[55,185],"interested":[56],"impact":[59],"adequate":[61,108,172,228,300],"inadequate":[63,84,99,191,248],"prosody,":[64,85],"here":[65],"particularly":[66],"terms":[68,307],"accent":[70],"placement,":[71],"on":[72,293,312,320],"aliveness":[77],"agents.":[80,140],"We":[81],"compare":[82],"(1)":[83],"as":[86,119,179,187,219,256,279],"generated":[87],"off-the-shelf":[89],"text-to-speech":[90],"(TTS)":[91],"engines":[92],"with":[93,149,247],"synthetic":[94,198,252],"output;":[95],"(2)":[96,196],"same":[98],"prosody":[100,109,173,192,249,301],"imitated":[101],"trained":[103],"human":[104,175,195,210,245,274],"speakers;":[105],"(3)":[107],"produced":[110],"those":[112,138],"speakers.":[113],"The":[114],"was":[116,254,263,276],"presented":[117,158],"audio-only":[120,268],"embodied,":[123],"anthropomorphic":[124],"agents,":[125],"investigate":[127],"potential":[129],"masking":[130,237],"effect":[131,238],"a":[133,209,244,251,260,285,331],"simultaneous":[134],"visual":[135],"representation":[136],"virtual":[139,261,286,328],"To":[141],"this":[142],"end,":[143],"conducted":[145],"an":[146,213],"online":[147],"study":[148],"40":[150],"participants":[151],"listening":[152],"four":[154],"different":[155],"dialogues":[156],"each":[157],"three":[161],"Speech":[162],"levels":[163],"two":[166],"Embodiment":[167],"Results":[169],"confirmed":[170],"that":[171,324],"natural":[181],"(and":[182],"alive)":[189],"than":[190],"both":[194],"(1).":[200],"Thus,":[201],"not":[204],"sufficient":[205],"just":[207],"use":[208],"for":[212,302],"natural\u2014it":[220],"decisive":[222],"whether":[223],"prosodic":[225],"realisation":[226],"not.":[230],"Furthermore,":[231],"surprisingly,":[233],"found":[235],"no":[236],"speaker":[240],"embodiment,":[241],"since":[242],"neither":[243],"nor":[250],"judged":[255,278],"natural,":[258],"when":[259,282],"agent":[262],"visible":[264],"compared":[265],"condition.":[269],"On":[270],"contrary,":[272],"even":[277],"less":[280],"\u201calive\u201d":[281],"accompanied":[283],"agent.":[287],"sum,":[289],"results":[291],"emphasize,":[292],"one":[295],"hand,":[296,323],"importance":[298],"naturalness,":[304],"especially":[305],"accents":[309],"being":[310],"placed":[311],"important":[313],"words":[314],"phrase,":[317],"while":[318],"showing,":[319],"other":[322],"embodiment":[326],"plays":[330],"minor":[332],"role":[333],"ratings":[337],"voices.":[339]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
