VoxAnchor uses mmWave radar to authenticate speech by matching acoustics to physical throat vibrations.
March 31, 2026
Original Paper
VoxAnchor: Grounding Speech Authenticity in Throat Vibration via mmWave Radar
arXiv · 2603.27562
The Takeaway
It creates a hardware-anchored, 'unforgeable' link for audio security that can detect localized edits and deepfakes at the word level. This provides a robust physical defense against audio forgeries that software-only detection methods struggle to identify.
From the abstract
Rapid advances in speech synthesis and audio editing have made realistic forgeries increasingly accessible, yet existing detection methods remain vulnerable to tampering or depend on visual/wearable sensors. In this paper, we present VoxAnchor, a system that physically grounds audio authentication in vocal dynamics by leveraging the inherent coherence between speech acoustics and radar-sensed throat vibrations. VoxAnchor uses contactless millimeter-wave radar to capture fine-grained throat vibra