{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T14:07:42Z","timestamp":1778940462555,"version":"3.51.4"},"reference-count":122,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T00:00:00Z","timestamp":1770422400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2022-04363"],"award-info":[{"award-number":["RGPIN-2022-04363"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32471109"],"award-info":[{"award-number":["32471109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Human Behavior: Artificial Humans"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.chbah.2026.100261","type":"journal-article","created":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T16:04:31Z","timestamp":1770480271000},"page":"100261","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Prosodic cues strengthen human-AI voice boundaries: Listeners do not easily perceive human speakers and AI clones as the same person"],"prefix":"10.1016","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3870-5041","authenticated-orcid":false,"given":"Wenjun","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9947-1552","authenticated-orcid":false,"given":"Marc D.","family":"Pell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5171-9774","authenticated-orcid":false,"given":"Xiaoming","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.chbah.2026.100261_bib1","doi-asserted-by":"crossref","DOI":"10.3390\/mti6070051","article-title":"Is natural necessary? Human voice versus synthetic voice for intelligent virtual agents","volume":"6","author":"Abdulrahman","year":"2022","journal-title":"Multimodal Technologies and Interaction"},{"issue":"10","key":"10.1016\/j.chbah.2026.100261_bib2","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1111\/j.1467-9280.2006.01790.x","article-title":"They all look the same to me (unless they\u2019re angry) from out-group homogeneity to out-group heterogeneity","volume":"17","author":"Ackerman","year":"2006","journal-title":"Psychological Science"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib3","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1111\/j.1473-4192.2007.00145.x","article-title":"Constructing \u201cotherness\u201d: Ideologies and differentiating speech styleAbstract","volume":"17","author":"Anderson","year":"2007","journal-title":"International Journal of Applied Linguistics"},{"key":"10.1016\/j.chbah.2026.100261_bib5","series-title":"Proceedings of the 34th international conference on neural information processing systems","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"10.1016\/j.chbah.2026.100261_bib6","series-title":"Proceedings of interspeech 2025","article-title":"Finding the human voice in AI: Insights on the perception of AI-voice clones from naturalness and similarity ratings","author":"Bakkouche","year":"2025"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib7","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-94170-3","article-title":"People are poorly equipped to detect AI-powered voice clones","volume":"15","author":"Barrington","year":"2025","journal-title":"Scientific Reports"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v067.i01","article-title":"Fitting linear mixed-effects models using lme4","volume":"67","author":"Bates","year":"2015","journal-title":"Journal of Statistical Software"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib9","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1121\/1.1332378","article-title":"Discrimination of non-native consonant contrasts varying in perceptual assimilation to the listener's native phonological system","volume":"109","author":"Best","year":"2001","journal-title":"Journal of the Acoustical Society of America"},{"issue":"10","key":"10.1016\/j.chbah.2026.100261_bib10","doi-asserted-by":"crossref","first-page":"3953","DOI":"10.1093\/cercor\/bhu282","article-title":"A neural marker for social bias toward In-group accents","volume":"25","author":"Bestelmeyer","year":"2014","journal-title":"Cerebral Cortex"},{"key":"10.1016\/j.chbah.2026.100261_bib11","series-title":"Praat: Doing phonetics by computer","author":"Boersma","year":"2021"},{"key":"10.1016\/j.chbah.2026.100261_bib12","article-title":"Attractive synthetic voices","volume":"6","author":"Bruder","year":"2025","journal-title":"Computers in Human Behavior: Artificial Humans"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v080.i01","article-title":"Brms: An R package for bayesian multilevel models using stan","volume":"80","author":"B\u00fcrkner","year":"2017","journal-title":"Journal of Statistical Software"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib14","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1037\/dec0000140","article-title":"Implicit effects of speaker accents and vocally-expressed confidence on decisions to trust","volume":"7","author":"Caballero","year":"2020","journal-title":"Decision"},{"key":"10.1016\/j.chbah.2026.100261_bib15","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.neuropsychologia.2016.06.003","article-title":"Magnetic resonance imaging of the brain and vocal tract: Applications to the study of speech production and language learning","volume":"98","author":"Carey","year":"2017","journal-title":"Neuropsychologia"},{"key":"10.1016\/j.chbah.2026.100261_bib16","article-title":"Voice-cloning artificial-intelligence speakers can also mimic human-specific vocal expression","author":"Chen","year":"2023","journal-title":"Preprints"},{"issue":"210","key":"10.1016\/j.chbah.2026.100261_bib17","doi-asserted-by":"crossref","DOI":"10.3791\/66913","article-title":"Memorization-based training and testing paradigm for robust vocal identity recognition in expressive speech using event-related potentials analysis","author":"Chen","year":"2024","journal-title":"Journal of Visualized Experiments"},{"key":"10.1016\/j.chbah.2026.100261_bib18","series-title":"Proc. Speech prosody 2024","article-title":"Inconsistent prosodies more severely impair speaker discrimination of artificial-intelligence-cloned than human talkers","author":"Chen","year":"2024"},{"key":"10.1016\/j.chbah.2026.100261_bib19","series-title":"Statistical power analysis for the behavioral sciences","author":"Cohen","year":"2013"},{"key":"10.1016\/j.chbah.2026.100261_bib20","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.specom.2021.10.003","article-title":"Prosodic alignment toward emotionally expressive speech: Comparing human and alexa model talkers","volume":"135","author":"Cohn","year":"2021","journal-title":"Speech Communication"},{"key":"10.1016\/j.chbah.2026.100261_bib21","author":"Corretg\u00e9"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib22","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/s12369-015-0329-4","article-title":"A survey of using vocal prosody to convey emotion in robot speech","volume":"8","author":"Crumpton","year":"2016","journal-title":"International Journal of Social Robotics"},{"key":"10.1016\/j.chbah.2026.100261_bib23","article-title":"Identifying synthetic voices\u2019 qualities for conversational agents","author":"Cuciniello","year":"2022","journal-title":"Applied Intelligence and Informatics, Reggio Calabria, Italy"},{"key":"10.1016\/j.chbah.2026.100261_bib24","series-title":"Social networks analysis and mining Cham","article-title":"Making social platforms accessible: Emotion-aware speech generation with integrated text analysis","author":"De","year":"2025"},{"issue":"5","key":"10.1016\/j.chbah.2026.100261_bib25","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1093\/cercor\/bhab255","article-title":"Communicative and affective components in processing auditory vitality forms: An fMRI study","volume":"32","author":"Di Cesare","year":"2022","journal-title":"Cerebral Cortex"},{"key":"10.1016\/j.chbah.2026.100261_bib26","doi-asserted-by":"crossref","DOI":"10.1016\/j.chbr.2024.100538","article-title":"Human performance in detecting deepfakes: A systematic review and meta-analysis of 56 papers","volume":"16","author":"Diel","year":"2024","journal-title":"Computers in Human Behavior Reports"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib27","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1177\/02627X02021002004","article-title":"Accents of guilt?:effects of regional accent, race, and crime type on attributions of guilt","volume":"21","author":"Dixon","year":"2002","journal-title":"Journal of Language and Social Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib28","first-page":"1","article-title":"Does criticism in a foreign accent hurt less?","author":"Dom\u00ednguez-Arriola","year":"2025","journal-title":"Language, Cognition and Neuroscience"},{"key":"10.1016\/j.chbah.2026.100261_bib29","series-title":"Bridging communication gaps in human and Human-AI interactions: The role of accented speech on neurocognitive mechanisms and social dynamics","year":"2025"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib30","doi-asserted-by":"crossref","first-page":"2860","DOI":"10.1121\/10.0032400","article-title":"Acoustic encoding of vocally expressed confidence and doubt in Chinese bidialectics","volume":"156","author":"Feng","year":"2024","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/j.chbah.2026.100261_bib31","doi-asserted-by":"crossref","first-page":"41","DOI":"10.4324\/9781315187280-3","article-title":"The continuum model: Ten years later","author":"Fiske","year":"2018","journal-title":"Social Cognition"},{"issue":"38","key":"10.1016\/j.chbah.2026.100261_bib32","doi-asserted-by":"crossref","first-page":"13795","DOI":"10.1073\/pnas.1401383111","article-title":"A language-familiarity effect for speaker discrimination without comprehension","volume":"111","author":"Fleming","year":"2014","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"5","key":"10.1016\/j.chbah.2026.100261_bib33","first-page":"1276","article-title":"Does a regional accent perturb speech processing?","volume":"32","author":"Floccia","year":"2006","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib34","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1002\/ejsp.862","article-title":"A meta-analysis of the effects of speakers' accents on interpersonal evaluations","volume":"42","author":"Fuertes","year":"2012","journal-title":"European Journal of Social Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib35","doi-asserted-by":"crossref","DOI":"10.1016\/j.chb.2023.107693","article-title":"How children speak with their voice assistant Sila depends on what they think about her","volume":"143","author":"Gampe","year":"2023","journal-title":"Computers in Human Behavior"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib36","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1177\/0261927X09359590","article-title":"Speaking with a nonnative accent: Perceptions of bias, communication difficulties, and belonging in the United States","volume":"29","author":"Gluszek","year":"2010","journal-title":"Journal of Language and Social Psychology"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib37","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.bandl.2012.04.017","article-title":"An ERP investigation of regional and foreign accent processing","volume":"122","author":"Goslin","year":"2012","journal-title":"Brain and Language"},{"key":"10.1016\/j.chbah.2026.100261_bib38","series-title":"The Oxford handbook of language prosody","author":"Gussenhoven","year":"2021"},{"key":"10.1016\/j.chbah.2026.100261_bib39","article-title":"Emotion-aware speech generation by utilizing prosody in artificial agents: A systematic review","author":"Hassani","year":"2025","journal-title":"Circuits, Systems, and Signal Processing"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib40","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s10772-023-10027-y","article-title":"The perception of artificial-intelligence (AI) based synthesized speech in younger and older adults","volume":"26","author":"Herrmann","year":"2023","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib41","doi-asserted-by":"crossref","first-page":"307","DOI":"10.2466\/pms.104.1.307-326","article-title":"Listeners' cognitive and affective reactions to English speakers with standard American English and Asian accents","volume":"104","author":"Hosoda","year":"2007","journal-title":"Perceptual and Motor Skills"},{"issue":"3","key":"10.1016\/j.chbah.2026.100261_bib42","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.3758\/s13428-022-01818-3","article-title":"The jena voice learning and memory test (JVLMT): A standardized tool for assessing the ability to learn and recognize voices","volume":"55","author":"Humble","year":"2023","journal-title":"Behavior Research Methods"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib43","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1177\/1747021819865833","article-title":"To believe or not to believe? How voice and accent information in speech alter listener impressions of trust","volume":"73","author":"Jiang","year":"2020","journal-title":"Quarterly Journal of Experimental Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib44","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.cortex.2015.02.002","article-title":"On how the brain decodes vocal cues about speaker confidence","volume":"66","author":"Jiang","year":"2015","journal-title":"Cortex"},{"key":"10.1016\/j.chbah.2026.100261_bib45","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.specom.2017.01.011","article-title":"The sound of confidence and doubt","volume":"88","author":"Jiang","year":"2017","journal-title":"Speech Communication"},{"key":"10.1016\/j.chbah.2026.100261_bib46","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1016\/j.neuroimage.2018.07.042","article-title":"Neural architecture underlying person perception from in-group and out-group voices","volume":"181","author":"Jiang","year":"2018","journal-title":"NeuroImage"},{"key":"10.1016\/j.chbah.2026.100261_bib47","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2020.101100","article-title":"Vocal tract shaping of emotional speech","volume":"64","author":"Kim","year":"2020","journal-title":"Computer Speech & Language"},{"key":"10.1016\/j.chbah.2026.100261_bib48","article-title":"\u201ceh? Aye!\u201d: Categorisation bias for natural human vs AI-augmented voices is influenced by dialect","volume":"4","author":"Kirk","year":"2025","journal-title":"Computers in Human Behavior: Artificial Humans"},{"key":"10.1016\/j.chbah.2026.100261_bib49","series-title":"2024 international conference on artificial intelligence in information and communication (ICAIIC)","article-title":"Advancing AI voice synthesis: Integrating emotional expression in multi-speaker voice generation","author":"Kolekar","year":"2024"},{"key":"10.1016\/j.chbah.2026.100261_bib50","series-title":"Doing bayesian data analysis","first-page":"359","article-title":"Chapter 13 - Goals, power, and sample size","author":"Kruschke","year":"2015"},{"issue":"1493","key":"10.1016\/j.chbah.2026.100261_bib51","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1098\/rstb.2007.2154","article-title":"Phonetic learning as a pathway to language: New data and native language magnet theory expanded (NLM-e)","volume":"363","author":"Kuhl","year":"2008","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"key":"10.1016\/j.chbah.2026.100261_bib52","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2020.593732","article-title":"The human takes it all: Humanlike synthesized voices are perceived as less eerie and more likable. Evidence from a subjective ratings study","volume":"14","author":"K\u00fchne","year":"2020","journal-title":"Frontiers in Neurorobotics"},{"key":"10.1016\/j.chbah.2026.100261_bib53","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cognition.2016.04.004","article-title":"Similar impressions of humanness for human and artificial singing voices in autism spectrum disorders","volume":"153","author":"Kuriki","year":"2016","journal-title":"Cognition"},{"key":"10.1016\/j.chbah.2026.100261_bib54","doi-asserted-by":"crossref","DOI":"10.1016\/j.brainres.2025.149897","article-title":"The influence of speaker accent on the neurocognitive processing of politeness","volume":"1865","author":"Lam","year":"2025","journal-title":"Brain Research"},{"key":"10.1016\/j.chbah.2026.100261_bib55","doi-asserted-by":"crossref","first-page":"175","DOI":"10.3389\/fpsyg.2011.00175","article-title":"Anti-voice adaptation suggests prototype-based coding of voice identity","volume":"2","author":"Latinus","year":"2011","journal-title":"Frontiers in Psychology"},{"issue":"12","key":"10.1016\/j.chbah.2026.100261_bib56","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1016\/j.cub.2013.04.055","article-title":"Norm-based coding of voice identity in human auditory cortex","volume":"23","author":"Latinus","year":"2013","journal-title":"Current Biology"},{"issue":"9","key":"10.1016\/j.chbah.2026.100261_bib57","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.1177\/1747021819836890","article-title":"Breaking voice identity perception: Expressive voices are more confusable for listeners","volume":"72","author":"Lavan","year":"2019","journal-title":"Quarterly Journal of Experimental Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib58","doi-asserted-by":"crossref","first-page":"90","DOI":"10.3758\/s13423-018-1497-7","article-title":"Flexible voices: Identity perception from variable vocal signals","volume":"26","author":"Lavan","year":"2019","journal-title":"Psychonomic Bulletin & Review"},{"issue":"9","key":"10.1016\/j.chbah.2026.100261_bib59","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0332692","article-title":"Voice clones sound realistic but not (yet) hyperrealistic","volume":"20","author":"Lavan","year":"2025","journal-title":"PLoS One"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib60","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-10295-w","article-title":"Listeners form average-based representations of individual voice identities","volume":"10","author":"Lavan","year":"2019","journal-title":"Nature Communications"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib61","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s44271-023-00001-4","article-title":"A model for person perception from familiar and unfamiliar voices","volume":"1","author":"Lavan","year":"2023","journal-title":"Communications Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib62","article-title":"Emmeans: Estimated marginal means, aka least-squares means","author":"Lenth","year":"2021","journal-title":"The Comprehensive R Archive Network"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib63","doi-asserted-by":"crossref","DOI":"10.1002\/wcs.1483","article-title":"Methodological considerations for interpreting the Language familiarity effect in talker processing","volume":"10","author":"Levi","year":"2019","journal-title":"WIREs Cognitive Science"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib64","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.3758\/s13428-012-0203-3","article-title":"Recognizing vocal emotions in mandarin Chinese: A validated database of Chinese vocal emotional stimuli","volume":"44","author":"Liu","year":"2012","journal-title":"Behavior Research Methods"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib65","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.1109\/TAFFC.2025.3573878","article-title":"A review of human emotion synthesis based on generative technology","volume":"16","author":"Ma","year":"2025","journal-title":"IEEE transactions on affective computing"},{"key":"10.1016\/j.chbah.2026.100261_bib66","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.neuropsychologia.2018.03.039","article-title":"Understanding the mechanisms of familiar voice-identity recognition in the human brain","volume":"116","author":"Maguinness","year":"2018","journal-title":"Neuropsychologia"},{"issue":"8","key":"10.1016\/j.chbah.2026.100261_bib67","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0285333","article-title":"Warning: Humans cannot reliably detect speech deepfakes","volume":"18","author":"Mai","year":"2023","journal-title":"PLoS One"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib68","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/cbs0000292","article-title":"French or qu\u00e9b\u00e9cois? How speaker accents shape implicit and explicit intergroup attitudes among francophones in Montr\u00e9al","volume":"54","author":"Mauchand","year":"2022","journal-title":"Canadian Journal of Behavioural Science\/Revue Canadienne des Sciences du Comportement"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib69","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/cbs0000292","article-title":"French or Qu\u00e9b\u00e9cois? How speaker accents shape implicit and explicit intergroup attitudes among francophones in Montr\u00e9al","volume":"54","author":"Mauchand","year":"2022","journal-title":"Canadian Journal of Behavioural Science\/Revue canadienne des sciences du comportement"},{"key":"10.1016\/j.chbah.2026.100261_bib70","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuropsychologia.2022.108356","article-title":"Listen to my feelings! how prosody and accent drive the empathic relevance of complaining speech","volume":"175","author":"Mauchand","year":"2022","journal-title":"Neuropsychologia"},{"issue":"3","key":"10.1016\/j.chbah.2026.100261_bib71","first-page":"a31","article-title":"Voice conversion and cloning: Psychological and ethical implications of intentionally synthesising familiar voice identities","volume":"13","author":"McGettigan","year":"2025","journal-title":"Journal of the British Academy"},{"issue":"9","key":"10.1016\/j.chbah.2026.100261_bib72","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1002\/ase.2524","article-title":"Voice-over anatomy lectures created by AI-voice cloning technology: A descriptive article","volume":"17","author":"Mogali","year":"2024","journal-title":"Anatomical Sciences Education"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib73","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/S0747-5632(02)00081-X","article-title":"Social perception of male and female computer synthesized speech","volume":"19","author":"Mullennix","year":"2003","journal-title":"Computers in Human Behavior"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib74","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1177\/1071181321651128","article-title":"Public perceptions towards synthetic voice technology","volume":"65","author":"Noah","year":"2021","journal-title":"Proceedings of the Human Factors and Ergonomics Society - Annual Meeting"},{"issue":"5","key":"10.1016\/j.chbah.2026.100261_bib75","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.tics.2025.01.010","article-title":"Understanding voice naturalness","volume":"29","author":"Nussbaum","year":"2025","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.chbah.2026.100261_bib76","article-title":"Sora 2 is here","year":"2025","journal-title":"OpenAI"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib77","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1177\/0261927X19884090","article-title":"One of Us: On the role of accent and race in real-time In-Group categorization","volume":"39","author":"Paladino","year":"2020","journal-title":"Journal of Language and Social Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib78","series-title":"The handbook of English pronunciation","article-title":"Indian English pronunciation","author":"Pandey","year":"2015"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib79","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1121\/1.397564","article-title":"Long\u2010term memory for unfamiliar voices","volume":"85","author":"Papcun","year":"1989","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/j.chbah.2026.100261_bib80","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib81","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1080\/02699931.2013.812033","article-title":"Cross-cultural emotional prosody recognition: Evidence from Chinese and British listeners","volume":"28","author":"Paulmann","year":"2014","journal-title":"Cognition & Emotion"},{"issue":"85","key":"10.1016\/j.chbah.2026.100261_bib82","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib83","doi-asserted-by":"crossref","first-page":"195","DOI":"10.3758\/s13428-018-01193-y","article-title":"PsychoPy2: Experiments in behavior made easy","volume":"51","author":"Peirce","year":"2019","journal-title":"Behavior Research Methods"},{"key":"10.1016\/j.chbah.2026.100261_bib84","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.specom.2021.10.004","article-title":"The N400 reveals implicit accent-induced prejudice","volume":"137","author":"P\u00e9lissier","year":"2022","journal-title":"Speech Communication"},{"key":"10.1016\/j.chbah.2026.100261_bib85","doi-asserted-by":"crossref","unstructured":"Pell, M.D., Cui, H., Mori, Y., & Jiang, X. (2026). Speak or shout? Nonverbal vocalizations promote rapid detection of emotions in vocal communication. PLoS One, 21(1), Article e0327529. 10.1371\/journal.pone.0327529.","DOI":"10.1371\/journal.pone.0327529"},{"key":"10.1016\/j.chbah.2026.100261_bib86","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10919-008-0065-7","article-title":"Recognizing emotions in a foreign language","volume":"33","author":"Pell","year":"2009","journal-title":"Journal of Nonverbal Behavior"},{"key":"10.1016\/j.chbah.2026.100261_bib87","article-title":"Emotion recognition from speech using wav2vec 2.0 embeddings","author":"Pepino","year":"2021","journal-title":"arXiv preprint"},{"key":"10.1016\/j.chbah.2026.100261_bib88","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.anbehav.2014.06.011","article-title":"Vocal indicators of body size in men and women: A meta-analysis","volume":"95","author":"Pisanski","year":"2014","journal-title":"Animal Behaviour"},{"issue":"3","key":"10.1016\/j.chbah.2026.100261_bib89","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1177\/0023830916648720","article-title":"Relative salience of speech rhythm and speech rate on perceived foreign accent in a second language","volume":"60","author":"Polyanskaya","year":"2017","journal-title":"Language and Speech"},{"key":"10.1016\/j.chbah.2026.100261_bib90","series-title":"Posit software","article-title":"RStudio: Integrated development environment for R","year":"2024"},{"key":"10.1016\/j.chbah.2026.100261_bib91","series-title":"R: A language and environment for statistical computing","year":"2024"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib92","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1111\/j.2044-8295.2011.02051.x","article-title":"When it matters how you pronounce it: The influence of regional accents on job interview outcome","volume":"102","author":"Raki\u0107","year":"2011","journal-title":"British Journal of Psychology"},{"issue":"10","key":"10.1016\/j.chbah.2026.100261_bib93","first-page":"19","article-title":"The media equation: How people treat computers, television, and new media like real people","volume":"10","author":"Reeves","year":"1996","journal-title":"Cambridge, UK"},{"key":"10.1016\/j.chbah.2026.100261_bib94","series-title":"Psych: Procedures for psychological, psychometric, and personality research","author":"Revelle","year":"2025"},{"key":"10.1016\/j.chbah.2026.100261_bib95","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1016\/j.chb.2017.08.044","article-title":"Effectiveness, attention, and recall of human and artificial voices in an advertising story. Prosody influence and functions of voices","volume":"77","author":"Rodero","year":"2017","journal-title":"Computers in Human Behavior"},{"issue":"7","key":"10.1016\/j.chbah.2026.100261_bib96","doi-asserted-by":"crossref","first-page":"1746","DOI":"10.1177\/14614448211024142","article-title":"Synthetic versus human voices in audiobooks: The human emotional intimacy effect","volume":"25","author":"Rodero","year":"2023","journal-title":"New Media & Society"},{"key":"10.1016\/j.chbah.2026.100261_bib97","series-title":"Text, speech and dialogue text, speech and dialogue, brno, Czech Republic","article-title":"Speech synthesis and uncanny valley","author":"Romportl","year":"2014"},{"key":"10.1016\/j.chbah.2026.100261_bib98","article-title":"Perception and social evaluation of cloned and recorded voices: Effects of familiarity and self-relevance","volume":"4","author":"Rosi","year":"2025","journal-title":"Computers in Human Behavior: Artificial Humans"},{"key":"10.1016\/j.chbah.2026.100261_bib99","series-title":"Python 3 reference manual","author":"Rossum","year":"2009"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib100","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1038\/s42003-024-06372-6","article-title":"Cortical-striatal brain network distinguishes deepfake from real speaker identity","volume":"7","author":"Roswandowitz","year":"2024","journal-title":"Communications Biology"},{"key":"10.1016\/j.chbah.2026.100261_bib101","article-title":"Human perception of audio deepfakes: The role of language and speaking style","author":"San Segundo","year":"2025","journal-title":"arXiv e-prints, arXiv-2512"},{"key":"10.1016\/j.chbah.2026.100261_bib102","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2022.787499","article-title":"Robot voices in daily life: Vocal human-likeness and application context as determinants of user acceptance","volume":"13","author":"Schreibelmayr","year":"2022","journal-title":"Frontiers in Psychology"},{"key":"10.1016\/j.chbah.2026.100261_bib103","series-title":"Computational paralinguistics: Emotion, affect and personality in speech and language processing","author":"Schuller","year":"2013"},{"key":"10.1016\/j.chbah.2026.100261_bib104","series-title":"APA handbook of nonverbal communication","first-page":"289","article-title":"The voice: From identity to interactions","author":"Scott","year":"2016"},{"issue":"4","key":"10.1016\/j.chbah.2026.100261_bib105","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3386867","article-title":"Voice in human\u2013agent interaction: A survey","volume":"54","author":"Seaborn","year":"2021","journal-title":"ACM Computing Surveys"},{"issue":"0","key":"10.1016\/j.chbah.2026.100261_bib106","article-title":"The effects of perceived ethnicity and prosodic accuracy on intelligibility, comprehensibility, and accentedness in L2 mandarin Chinese","volume":"0","author":"Squizzero","year":"2025","journal-title":"Language and Speech"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib107","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.ijhcs.2005.07.002","article-title":"Persuasion and social perception of human vs. synthetic voice across person as source and computer as source conditions","volume":"64","author":"Stern","year":"2006","journal-title":"International Journal of Human-Computer Studies"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib108","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.jml.2005.02.003","article-title":"Audiovisual prosody and feeling of knowing","volume":"53","author":"Swerts","year":"2005","journal-title":"Journal of Memory and Language"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib109","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1002\/ejsp.2420010202","article-title":"Social categorization and intergroup behaviour","volume":"1","author":"Tajfel","year":"1971","journal-title":"European Journal of Social Psychology"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib110","doi-asserted-by":"crossref","first-page":"8799","DOI":"10.1038\/srep08799","article-title":"Involvement of the left insula in the ecological validity of the human voice","volume":"5","author":"Tamura","year":"2015","journal-title":"Scientific Reports"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib111","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1214\/20-BA1221","article-title":"Rank-normalization, folding, and localization: An improved R\u02c6 for assessing convergence of MCMC (with discussion)","volume":"16","author":"Vehtari","year":"2021","journal-title":"Bayesian analysis"},{"issue":"3","key":"10.1016\/j.chbah.2026.100261_bib112","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental algorithms for scientific computing in python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nature Methods"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib113","doi-asserted-by":"crossref","first-page":"35","DOI":"10.3758\/s13423-017-1343-3","article-title":"Bayesian inference for psychology. Part I: Theoretical advantages and practical ramifications","volume":"25","author":"Wagenmakers","year":"2018","journal-title":"Psychonomic Bulletin & Review"},{"key":"10.1016\/j.chbah.2026.100261_bib114","series-title":"Proceedings of the 2024 on ACM SIGSAC conference on computer and communications security (CCS \u201824)","article-title":"Better be computer or I'm dumb\u201d: A large-scale evaluation of humans as audio deepfake detectors","author":"Warren","year":"2024"},{"issue":"1","key":"10.1016\/j.chbah.2026.100261_bib115","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1177\/14705958231216936","article-title":"Language as a source of otherness","volume":"24","author":"Wilmot","year":"2024","journal-title":"International Journal of Cross Cultural Management"},{"issue":"6","key":"10.1016\/j.chbah.2026.100261_bib116","doi-asserted-by":"crossref","first-page":"4524","DOI":"10.1121\/1.2913046","article-title":"Identification and discrimination of bilingual talkers across languages","volume":"123","author":"Winters","year":"2008","journal-title":"Journal of the Acoustical Society of America"},{"issue":"2","key":"10.1016\/j.chbah.2026.100261_bib117","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1093\/applin\/amad055","article-title":"Capturing thresholds and continuities: Individual differences as predictors of L2 sociolinguistic repertoires in adult migrant learners in Austria","volume":"45","author":"Wirtz","year":"2024","journal-title":"Applied Linguistics"},{"key":"10.1016\/j.chbah.2026.100261_bib118","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing: System demonstrations online","article-title":"Transformers: state-of-the-art natural language processing","author":"Wolf","year":"2020"},{"key":"10.1016\/j.chbah.2026.100261_bib119","series-title":"The routledge handbook of phonetics","first-page":"314","article-title":"Prosody, tone, and intonation","author":"Xu","year":"2019"},{"issue":"7","key":"10.1016\/j.chbah.2026.100261_bib120","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1177\/1747021821998557","article-title":"Influence of emotional prosody, content, and repetition on memory recognition of speaker identity","volume":"74","author":"Xu","year":"2021","journal-title":"Quarterly Journal of Experimental Psychology"},{"issue":"3","key":"10.1016\/j.chbah.2026.100261_bib121","doi-asserted-by":"crossref","first-page":"86","DOI":"10.3758\/s13428-025-02608-3","article-title":"Introducing the sisu voice matching test (SVMT): A novel tool for assessing voice discrimination in Chinese","volume":"57","author":"Xu","year":"2025","journal-title":"Behavior Research Methods"},{"key":"10.1016\/j.chbah.2026.100261_bib123","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.cortex.2017.06.005","article-title":"It doesn't matter what you say: FMRI correlates of voice learning and recognition independent of speech content","volume":"94","author":"Z\u00e4ske","year":"2017","journal-title":"Cortex"},{"issue":"10","key":"10.1016\/j.chbah.2026.100261_bib124","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0275915","article-title":"Cultural differences in vocal expression analysis: Effects of task, language, and stimulus-related factors","volume":"17","author":"Zhang","year":"2022","journal-title":"PLoS One"}],"container-title":["Computers in Human Behavior: Artificial Humans"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2949882126000125?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2949882126000125?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T13:15:34Z","timestamp":1778937334000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2949882126000125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":122,"alternative-id":["S2949882126000125"],"URL":"https:\/\/doi.org\/10.1016\/j.chbah.2026.100261","relation":{"has-preprint":[{"id-type":"doi","id":"10.31234\/osf.io\/qz9mu_v1","asserted-by":"object"}]},"ISSN":["2949-8821"],"issn-type":[{"value":"2949-8821","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Prosodic cues strengthen human-AI voice boundaries: Listeners do not easily perceive human speakers and AI clones as the same person","name":"articletitle","label":"Article Title"},{"value":"Computers in Human Behavior: Artificial Humans","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.chbah.2026.100261","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100261"}}