# Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Video

arXiv: https://arxiv.org/abs/2202.12883 · HTML: https://mlsanity.com/paper/2202.12883/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 118 references that are in the map.
- First posted on arXiv 25 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [DeepFaceLab: Integrated, flexible and extensible face-swapping framework](https://mlsanity.com/paper/2005.05535/) (2020)
- [Neural Voice Cloning with a Few Samples](https://mlsanity.com/paper/1802.06006/) (2018)
- [TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation](https://mlsanity.com/paper/1801.05746/) (2018)
- [LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization](https://mlsanity.com/paper/2106.04185/) (2021)
- [Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds](https://mlsanity.com/paper/2105.06496/) (2021)
- [DeepFake Detection: Current Challenges and Next Steps](https://mlsanity.com/paper/2003.09234/) (2020)
- [Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion](https://mlsanity.com/paper/2112.10936/) (2021)
- [NAUTILUS: a Versatile Voice Cloning System](https://mlsanity.com/paper/2005.11004/) (2020)
- [Images and Misinformation in Political Groups: Evidence from WhatsApp in India](https://mlsanity.com/paper/2005.09784/) (2020)
- [The Deepfake Detection Dilemma: A Multistakeholder Exploration of Adversarial Dynamics in Synthetic Media](https://mlsanity.com/paper/2102.06109/) (2021)
- [Human detection of machine manipulated media](https://mlsanity.com/paper/1907.05276/) (2019)

## Built on by (most cited first, 16 of 16)

- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)
- [A Representative Study on Human Detection of Artificially Generated Media Across Countries](https://mlsanity.com/paper/2312.05976/) (2023)
- [As Good As A Coin Toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli](https://mlsanity.com/paper/2403.16760/) (2024)
- [Characterizing Photorealism and Artifacts in Diffusion Model-Generated Images](https://mlsanity.com/paper/2502.11989/) (2025)
- [People are poorly equipped to detect AI-powered voice clones](https://mlsanity.com/paper/2410.03791/) (2024)
- [Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation](https://mlsanity.com/paper/2408.00024/) (2024)
- [More Human or More AI? Visualizing Human-AI Collaboration Disclosures in Journalistic News Production](https://mlsanity.com/paper/2601.11072/) (2026)
- [Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms](https://mlsanity.com/paper/2402.03188/) (2024)
- [Designing Effective Digital Literacy Interventions for Boosting Deepfake Discernment](https://mlsanity.com/paper/2507.23492/) (2025)
- [On Deepfake Voice Detection -- It's All in the Presentation](https://mlsanity.com/paper/2509.26471/) (2025)
- [Seeing, Hearing, and Knowing Together: Multimodal Strategies in Deepfake Videos Detection](https://mlsanity.com/paper/2602.01284/) (2026)
- [Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes](https://mlsanity.com/paper/2605.04797/) (2026)
- [Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection](https://mlsanity.com/paper/2605.19360/) (2026)
- [A survey of AI-generated voices and their detection](https://mlsanity.com/paper/2608.15411/) (2026)
- [Can Tainted Pixels Expose Deepfake Videos?](https://mlsanity.com/paper/2608.27492/) (2026)

## Abstract (arXiv)

Recent advances in technology for hyper-realistic visual and audio effects provoke the concern that deepfake videos of political speeches will soon be indistinguishable from authentic video recordings. The conventional wisdom in communication theory predicts people will fall for fake news more often when the same version of a story is presented as a video versus text. We conduct 5 pre-registered randomized experiments with 2,215 participants to evaluate how accurately humans distinguish real political speeches from fabrications across base rates of misinformation, audio sources, question framings, and media modalities. We find base rates of misinformation minimally influence discernment and deepfakes with audio produced by the state-of-the-art text-to-speech algorithms are harder to discern than the same deepfakes with voice actor audio. Moreover across all experiments, we find audio and visual information enables more accurate discernment than text alone: human discernment relies more on how something is said, the audio-visual cues, than what is said, the speech content.