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

• URL: http://arxiv.org/abs/2605.26136v1
• Date: Thu, 21 May 2026 21:22:44 GMT
• Title: Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception
• Abstract summary: We present the largest listening study on audio deepfake perception to date.<n>We collected 35,532 judgments from 1,768 participants across 138 text-to-speech and voice conversion systems.
• Score: 5.116378112926705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection [12.159476982130286]
  Speech deepfakes can mimic a speaker's voice convincingly enough to deceive listeners and automated systems.<n>Most detectors end with one score per utterance, but it says little about why a borderline item should be trusted, deferred, or reviewed.<n>We answer this question with an auditable decision record that carries four aligned cues into a late calibration step.
  arXiv  Detail & Related papers  (2026-09-08T15:38:57Z)
• Tracking the Trend in How Speech Synthesizers Deceive People [0.15635627702544694]
  We compare human detection for three selected voice synthesis tools released in 2019, 2022, and 2024 with 82 IT professionals.<n>For fully synthetic speech (full spoofs), the F1 score drops from about 90% for RTVC and YourTTS to 48% for ElevenLabs.<n>For partial spoofing, where only one sentence of an utterance is altered, strict accuracy falls to 9%.
  arXiv  Detail & Related papers  (2026-08-20T12:27:37Z)
• Evaluating Commercial AI Chatbots as News Intermediaries [85.32040752972836]
  Best systems achieve over 90% multiple-choice accuracy on questions about events reported hours earlier.<n>Every model achieves its lowest accuracy on Hindi.<n> retrieval, not reasoning, failures drive over 70% of all errors.
  arXiv  Detail & Related papers  (2026-05-21T17:42:07Z)
• What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection [7.555970188701627]
  We introduce transcript-level adversarial attacks against open-source and commercial anti-spoofing detectors.<n>Attack success rates surpass 60% on several open-source detector-voice pairs, and one commercial detection accuracy drops from 100% on synthetic audio to just 32%.<n>Results highlight the need to move beyond purely acoustic defenses and account for linguistic variation in the design of robust anti-spoofing systems.
  arXiv  Detail & Related papers  (2025-05-23T06:06:37Z)
• Measuring the Robustness of Audio Deepfake Detectors [59.09338266364506]
  This work systematically evaluates the robustness of 10 audio deepfake detection models against 16 common corruptions.<n>Using both traditional deep learning models and state-of-the-art foundation models, we make four unique observations.
  arXiv  Detail & Related papers  (2025-03-21T23:21:17Z)
• Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024 [6.865766644176186]
  We introduce Deepfake-Eval-2024, a new deepfake detection benchmark consisting of in-the-wild deepfakes collected from social media and deepfake detection platform users in 2024.<n>The benchmark contains diverse media content from 88 different websites in 52 different languages.<n>We find that the performance of open-source state-of-the-art deepfake detection models drops precipitously when evaluated on Deepfake-Eval-2024.
  arXiv  Detail & Related papers  (2025-03-04T18:33:22Z)
• I Can Hear You: Selective Robust Training for Deepfake Audio Detection [16.52185019459127]
  We establish the largest public voice dataset to date, named DeepFakeVox-HQ, comprising 1.3 million samples. Despite previously reported high accuracy, existing deepfake voice detectors struggle with our diversely collected dataset. We propose the F-SAT: Frequency-Selective Adversarial Training method focusing on high-frequency components.
  arXiv  Detail & Related papers  (2024-10-31T18:21:36Z)
• Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes [49.81915942821647]
  This paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-ofthe-art audiovisual deepfake detection models. We found that all AI models performed better than humans when evaluated on the same 40 videos.
  arXiv  Detail & Related papers  (2024-05-07T07:57:15Z)
• Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models [52.04189118767758]
  Generalization is a main issue for current audio deepfake detectors. In this paper we study the potential of large-scale pre-trained models for audio deepfake detection.
  arXiv  Detail & Related papers  (2024-05-03T15:27:11Z)
• PITCH: AI-assisted Tagging of Deepfake Audio Calls using Challenge-Response [14.604998731837595]
  We develop PITCH, a robust challenge-response method to detect and tag interactive deepfake audio calls.<n>PITCH's challenges enhanced machine detection capabilities to 88.7% AUROC score.<n>We develop a novel human-AI collaborative system that tags suspicious calls as "Deepfake-likely"
  arXiv  Detail & Related papers  (2024-02-28T06:17:55Z)
• Deepfake audio detection by speaker verification [79.99653758293277]
  We propose a new detection approach that leverages only the biometric characteristics of the speaker, with no reference to specific manipulations. The proposed approach can be implemented based on off-the-shelf speaker verification tools. We test several such solutions on three popular test sets, obtaining good performance, high generalization ability, and high robustness to audio impairment.
  arXiv  Detail & Related papers  (2022-09-28T13:46:29Z)
• Adversarially robust deepfake media detection using fused convolutional neural network predictions [79.00202519223662]
  Current deepfake detection systems struggle against unseen data. We employ three different deep Convolutional Neural Network (CNN) models to classify fake and real images extracted from videos. The proposed technique outperforms state-of-the-art models with 96.5% accuracy.
  arXiv  Detail & Related papers  (2021-02-11T11:28:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.