AI & ML Practical Magic

A 3D-printable plastic structure can hide your identity from voice-recognition AI while leaving your speech perfectly clear to human ears.

April 23, 2026

Original Paper

Before the Mic: Physical-Layer Voiceprint Anonymization with Acoustic Metamaterials

Zhiyuan Ning, Zhanyong Tang, Xiaojiang Chen, Zheng Wang

arXiv · 2604.20116

The Takeaway

Biometric voiceprints are increasingly used for security and tracking without a person's consent. This acoustic metamaterial physically distorts the sound of a voice before it even reaches a microphone. Human listeners hear a normal conversation, but the digital signature of the speaker becomes unrecognizable to identification software. The device requires no power or electronic parts to function as a physical privacy shield. This technology could give people a way to protect their biometric data in a world of constant surveillance.

From the abstract

Voiceprints are widely used for authentication; however, they are easily captured in public settings and cannot be revoked once leaked. Existing anonymization systems operate inside recording devices, which makes them ineffective when microphones or software are untrusted, as in conference rooms, lecture halls, and interviews. We present EchoMask, the first practical physical-layer system for real-time voiceprint anonymization using acoustic metamaterials. By modifying sound waves before they re