I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Erscoi, Lelia, Kinnunen, Tomi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914607151448064
author Erscoi, Lelia
Kinnunen, Tomi
author_facet Erscoi, Lelia
Kinnunen, Tomi
contents Automatic deepfake detection has received considerable research attention, yet the socio-technical environment in which humans actually encounter synthetic speech remains poorly understood. We investigate voice deepfake detection as a perceptual and contextual process, presenting a localization task in which 47 participants marked suspected synthetic segments across authentic, fully synthetic, and partially synthetic utterances under three manipulated trust cues: instructional framing, affective priming, and provenance labeling. Participants provided quality ratings on mechanicalness, expressiveness, intelligibility, clarity, calmness, and confidence of evaluation. Utterance class was the primary determinant of detection accuracy and perceptual quality; trust cues produced no main effects but motivated detection behavior. Fully synthetic speech was detected at below-chance levels. Quality ratings tracked utterance type, indicating implicit discrimination where overt detection failed.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28064
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
Erscoi, Lelia
Kinnunen, Tomi
Audio and Speech Processing
Artificial Intelligence
Human-Computer Interaction
Automatic deepfake detection has received considerable research attention, yet the socio-technical environment in which humans actually encounter synthetic speech remains poorly understood. We investigate voice deepfake detection as a perceptual and contextual process, presenting a localization task in which 47 participants marked suspected synthetic segments across authentic, fully synthetic, and partially synthetic utterances under three manipulated trust cues: instructional framing, affective priming, and provenance labeling. Participants provided quality ratings on mechanicalness, expressiveness, intelligibility, clarity, calmness, and confidence of evaluation. Utterance class was the primary determinant of detection accuracy and perceptual quality; trust cues produced no main effects but motivated detection behavior. Fully synthetic speech was detected at below-chance levels. Quality ratings tracked utterance type, indicating implicit discrimination where overt detection failed.
title I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
topic Audio and Speech Processing
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2605.28064