{"id":"https://openalex.org/W4414854681","doi":"https://doi.org/10.48550/arxiv.2505.13455","title":"Spatiotemporal Emotional Synchrony in Dyadic Interactions: The Role of Speech Conditions in Facial and Vocal Affective Alignment","display_name":"Spatiotemporal Emotional Synchrony in Dyadic Interactions: The Role of Speech Conditions in Facial and Vocal Affective Alignment","publication_year":2025,"publication_date":"2025-04-29","ids":{"openalex":"https://openalex.org/W4414854681","doi":"https://doi.org/10.48550/arxiv.2505.13455"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.13455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13455","pdf_url":"https://arxiv.org/pdf/2505.13455","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.13455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037639226","display_name":"Von Ralph Dane Marquez Herbuela","orcid":"https://orcid.org/0000-0003-4840-0153","observed_orcids":["https://orcid.org/0000-0003-4840-0153"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herbuela, Von Ralph Dane Marquez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067742588","display_name":"Yukie Nagai","orcid":"https://orcid.org/0000-0003-4794-0940","observed_orcids":["https://orcid.org/0000-0003-4794-0940"]},"institutions":[{"id":"https://openalex.org/I4405287662","display_name":"International Research Center for Neurointelligence, The University of Tokyo","ror":"https://ror.org/05t86na81","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4405287662","https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nagai, Yukie","raw_affiliation_strings":["International Research Center for Neurointelligence The University of Tokyo Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Research Center for Neurointelligence The University of Tokyo Tokyo , Japan","institution_ids":["https://openalex.org/I4405287662"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.98580002784729,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.98580002784729,"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/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.004900000058114529,"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/T11431","display_name":"Action Observation and Synchronization","score":0.0020000000949949026,"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/emotional-synchrony","display_name":"emotional synchrony","score":0.9520000219345093},{"id":"https://openalex.org/keywords/dyadic-interaction","display_name":"dyadic interaction","score":0.7739999890327454},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.8309999704360962},{"id":"https://openalex.org/keywords/facial-expressions","display_name":"facial expressions","score":0.6449999809265137},{"id":"https://openalex.org/keywords/vocal-emotion","display_name":"vocal emotion","score":0.8159999847412109},{"id":"https://openalex.org/keywords/valence-and-arousal","display_name":"valence and arousal","score":0.7549999952316284},{"id":"https://openalex.org/keywords/turn-taking","display_name":"turn-taking","score":0.7509999871253967},{"id":"https://openalex.org/keywords/time-lag-analysis","display_name":"lag analysis","score":0.6010000109672546},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"dynamic time warping","score":0.7710000276565552},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.8230000138282776},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.8379999995231628},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5842000246047974},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47040000557899475},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4140999913215637},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C75778745","wikidata":"https://www.wikidata.org/wiki/Q342626","display_name":"Lag","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C3020774634","wikidata":"https://www.wikidata.org/wiki/Q3113318","display_name":"Emotional valence","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.13455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13455","pdf_url":"https://arxiv.org/pdf/2505.13455","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2505.13455","doi":"https://doi.org/10.48550/arxiv.2505.13455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.13455","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.13455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13455","pdf_url":"https://arxiv.org/pdf/2505.13455","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414854681.pdf","grobid_xml":"https://content.openalex.org/works/W4414854681.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417347398","https://openalex.org/W2028899742","https://openalex.org/W2011461592","https://openalex.org/W2117752179","https://openalex.org/W2161450073","https://openalex.org/W2781617601","https://openalex.org/W6963149791","https://openalex.org/W2955597114","https://openalex.org/W3211323766","https://openalex.org/W2169099996"],"abstract_inverted_index":{"Understanding":[0],"how":[1,46],"humans":[2],"express":[3],"and":[4,14,23,53,58,62,81,94,105,120,132,148,167,212,219],"synchronize":[5],"emotions":[6],"across":[7,60],"multiple":[8],"communication":[9,211],"channels":[10],"particularly":[11],"facial":[12,61,186],"expressions":[13,187],"speech":[15,33,40,92,114,138,163,191,195],"has":[16],"significant":[17],"implications":[18],"for":[19,143],"emotion":[20,75],"recognition":[21],"systems":[22],"human":[24],"computer":[25],"interaction.":[26,229],"Motivated":[27],"by":[28],"the":[29,51,69,203,217],"notion":[30],"that":[31,185],"non-overlapping":[32],"promotes":[34],"clearer":[35],"emotional":[36,95,122,210],"coordination,":[37],"while":[38,194],"overlapping":[39,113,125,137,162],"disrupts":[41],"synchrony,":[42],"this":[43],"study":[44],"examines":[45],"these":[47,158],"conversational":[48,206],"dynamics":[49,221],"shape":[50],"spatial":[52,218],"temporal":[54,155,220],"alignment":[55,96,156,176,225],"of":[56,205,222],"arousal":[57],"valence":[59],"vocal":[63],"modalities.":[64],"Using":[65],"dyadic":[66],"interactions":[67],"from":[68],"IEMOCAP":[70],"dataset,":[71],"we":[72],"extracted":[73],"continuous":[74],"estimates":[76],"via":[77],"EmoNet":[78],"(facial":[79],"video)":[80],"a":[82],"Wav2Vec2-based":[83],"model":[84],"(speech":[85],"audio).":[86],"Segments":[87],"were":[88,130],"categorized":[89],"based":[90],"on":[91],"overlap,":[93],"was":[97,115],"assessed":[98],"using":[99],"Pearson":[100],"correlation,":[101],"lag":[102,169],"adjusted":[103,146],"analysis,":[104],"Dynamic":[106],"Time":[107],"Warping":[108],"(DTW).":[109],"Across":[110],"analyses,":[111],"non":[112,136],"associated":[116],"with":[117],"more":[118,153,188],"stable":[119],"predictable":[121],"synchrony":[123],"than":[124],"speech.":[126],"While":[127],"zero-lag":[128],"correlations":[129,147],"low":[131],"not":[133],"statistically":[134],"different,":[135],"showed":[139,184],"reduced":[140],"variability,":[141],"especially":[142],"arousal.":[144],"Lag":[145],"best-lag":[149],"distributions":[150],"revealed":[151],"clearer,":[152],"consistent":[154],"in":[157,208,226],"segments.":[159],"In":[160],"contrast,":[161],"exhibited":[164],"higher":[165],"variability":[166],"flatter":[168],"profiles,":[170],"though":[171],"DTW":[172],"indicated":[173],"unexpectedly":[174],"tighter":[175],"suggesting":[177],"distinct":[178],"coordination":[179],"strategies.":[180],"Notably,":[181],"directionality":[182],"patterns":[183],"often":[189],"preceded":[190],"during":[192,197],"turn-taking,":[193],"led":[196],"simultaneous":[198],"vocalizations.":[199],"These":[200],"findings":[201],"underscore":[202],"importance":[204],"structure":[207],"regulating":[209],"provide":[213],"new":[214],"insight":[215],"into":[216],"multimodal":[223],"affective":[224],"real":[227],"world":[228]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2025-10-10T00:00:00"}