VoxAnchor: Grounding Speech Authenticity in Throat Vibration via mmWave Radar

TL;DR

VoxAnchor leverages millimeter-wave radar to detect speech forgeries by analyzing throat vibrations, providing a physiologically grounded, fine-grained authentication method that outperforms existing techniques.

Contribution

The paper introduces VoxAnchor, a novel system that physically grounds speech authentication in throat vibrations using radar, enabling robust, word-level forgery detection.

Findings

Achieves an overall EER of 0.017 in forgery detection.

Effectively detects diverse forgeries including editing, splicing, replay, and deepfake.

Operates with low latency and modest computational cost.

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 vibrations that are tightly coupled with human speech production, establishing a hard-to-forge anchor rooted in human physiology. The design comprises three main components: (1) a cross-modal frame-work that uses modality-specific encoders and contrastive learning to detect subtle mismatches at word granularity; (2) a phase-aware pipeline that extracts physically consistent, temporally faithful throat vibrations; and (3) a dual-stage strategy that combines signal-level onset detection and semantic-level coherence to align asynchronous radar and audio streams. Unlike liveness detection, which only confirms whether speech occurred, VoxAnchor verifies what was spoken through word-level content consistency, exposing localized edits that preserve identity and global authenticity cues. Extensive evaluations show that VoxAnchor achieves robust, fine-grained detection across diverse forgeries (editing, splicing, replay, deepfake) and conditions, with an overall EER of 0.017, low latency, and modest computational cost.