Voice Morphing: Two Identities in One Voice

TL;DR

This paper introduces Voice Identity Morphing (VIM), a novel voice-based morph attack that can generate speech samples impersonating two different individuals, exposing vulnerabilities in speaker recognition systems.

Contribution

It is the first to demonstrate voice morphing attacks that can impersonate two identities, highlighting security risks in voice biometric systems.

Findings

VIM achieves over 80% success rate in fooling recognition systems.

VIM effectively impersonates two identities in speech samples.

Vulnerabilities are demonstrated on ECAPA-TDNN and x-vector systems.

Abstract

In a biometric system, each biometric sample or template is typically associated with a single identity. However, recent research has demonstrated the possibility of generating "morph" biometric samples that can successfully match more than a single identity. Morph attacks are now recognized as a potential security threat to biometric systems. However, most morph attacks have been studied on biometric modalities operating in the image domain, such as face, fingerprint, and iris. In this preliminary work, we introduce Voice Identity Morphing (VIM) - a voice-based morph attack that can synthesize speech samples that impersonate the voice characteristics of a pair of individuals. Our experiments evaluate the vulnerabilities of two popular speaker recognition systems, ECAPA-TDNN and x-vector, to VIM, with a success rate (MMPMR) of over 80% at a false match rate of 1% on the Librispeech dataset.