Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation

TL;DR

This paper introduces an adversarial autoencoding approach to disentangle and conceal specific speaker attributes, like sex, in neural voice representations, enhancing privacy in speaker verification tasks without sacrificing recognition accuracy.

Contribution

It presents a novel attribute-driven privacy preservation method using adversarial autoencoding to selectively hide sensitive speaker information.

Findings

Successfully conceals sex attribute in voice representations

Maintains speaker verification performance

Demonstrates effectiveness on VoxCeleb dataset

Abstract

In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authentication. Modern vocal representations of the speaker are based on neural embeddings. In addition to the targeted information, these representations usually contain sensitive information about the speaker, like the age, sex, physical state, education level or ethnicity. In order to allow the user to choose which information to protect, we introduce in this paper the concept of attribute-driven privacy preservation in speaker voice representation. It allows a person to hide one or more personal aspects to a potential malicious interceptor and to the application provider. As a first solution to this concept, we propose to use an adversarial autoencoding method that disentangles in the voice representation a given speaker attribute thus allowing its concealment. We focus here on the sex attribute for an Automatic Speaker Verification (ASV) task. Experiments carried out using the VoxCeleb datasets have shown that the proposed method enables the concealment of this attribute while preserving ASV ability.