Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception

Authors: Nicolas M. Müller, Wei Herng Choong

Published: 2026-05-21 21:22:44+00:00

AI Summary

This paper presents the largest listening study on human audio deepfake perception to date, collecting 35,532 judgments from 1,768 participants across 138 text-to-speech and voice conversion systems. The study reveals a "skepticism shift," where human accuracy on real audio dropped significantly (from 72.7% to 64.1%) compared to a 2021 baseline, while accuracy on fake samples remained stable. This suggests that the primary threat of modern deepfakes is the erosion of trust in genuine audio, rather than merely deception.

Abstract

Audio deepfakes have improved rapidly recently, yet their effect on human trust in real speech remains unstudied. We present the largest listening study on audio deepfake perception to date, collecting 35,532 judgments from 1,768 participants across 138 text-to-speech and voice conversion systems. Our central finding is a skepticism shift: compared to a 2021 baseline, human accuracy on fake samples barely changed (72.9% to 71.2%), but accuracy on real samples dropped from 72.7% to 64.1%. Participants are not worse at detecting synthesis artifacts; rather, they increasingly distrust authentic speech. Samples generated by commercial and autoregressive language model systems proved hardest to detect (61.3 - 65.9%), while those from traditional seq2seq and flow-matching models remain easier to spot (75.4 - 76.8%). An ML detector that served as a reference point maintained over 94.5% accuracy across all conditions. Our results suggest that the primary threat posed by modern deepfakes may not be mere deception, but the erosion of trust in genuine audio.