Alethia is a pretrained audio encoder using continuous embedding prediction and generative flow-matching reconstruction that outperforms existing speech foundation models on voice deepfake tasks with better robustness and zero-shot generalization.
R., Naini, A
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
An experiment shows humans detect fully synthetic speech below chance but exhibit implicit discrimination via quality ratings in a localization task with trust cue manipulations.
citing papers explorer
-
Alethia: A Foundational Encoder for Voice Deepfakes
Alethia is a pretrained audio encoder using continuous embedding prediction and generative flow-matching reconstruction that outperforms existing speech foundation models on voice deepfake tasks with better robustness and zero-shot generalization.
-
I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
An experiment shows humans detect fully synthetic speech below chance but exhibit implicit discrimination via quality ratings in a localization task with trust cue manipulations.