RadEar: A Self-Supervised RF Backscatter System for Voice Eavesdropping and Separation

TL;DR

RadEar is a novel RF backscatter system that covertly eavesdrops on and separates human speech through walls using self-supervised learning, achieving high-fidelity voice recovery without ground-truth labels.

Contribution

It introduces a batteryless RF backscatter tag with energy-efficient modulation and a self-supervised RF reader for voice separation, enabling covert and effective eavesdropping in real-world scenarios.

Findings

Successfully recovers human speech through walls with high fidelity

Employs self-supervised learning for voice separation without labeled data

Demonstrates practical covert eavesdropping capabilities

Abstract

Eavesdropping on voice conversations presents a growing threat to personal privacy and information security. In this paper, we present RadEar, a novel RF backscatter-based system designed to enable covert voice eavesdropping through walls. RadEar consists of two key components: (i) a batteryless RF backscatter tag covertly deployed inside the target space, and (ii) an RF reader located outside the room that performs signal demodulation, voice separation, and denoising. The tag features a compact, dual-resonator design that achieves energy-efficient frequency modulation for continuous voice eavesdropping while mitigating self-interference by separating excitation and reflection frequencies. To overcome the challenges of weak signal reception and overlapping speech, the RF reader employs self-supervised learning models for voice separation and denoising, trained using a remix-based objective without requiring ground-truth labels. We fabricate and evaluate RadEar in real-world scenarios, demonstrating its ability to recover and separate human speech with high fidelity under practical constraints.