Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation

by   Paul-Gauthier Noé, et al.

With the increasing interest over speech technologies, numerous Automatic Speaker Verification (ASV) systems are employed to perform person identification. In the latter context, the systems rely on neural embeddings as a speaker representation. Nonetheless, such representations may contain privacy sensitive information about the speakers (e.g. age, sex, ethnicity, ...). In this paper, we introduce the concept of attribute-driven privacy preservation that enables a person to hide one or a few personal aspects to the authentication component. As a first solution we define an adversarial autoencoding method that disentangles a given speaker attribute from its neural representation. The proposed approach is assessed with a focus on the sex attribute. Experiments carried out using the VoxCeleb data sets have shown that the defined model enables the manipulation (i.e. variation or hiding) of this attribute while preserving good ASV performance.


page 1

page 2

page 3

page 4


Leveraging speaker attribute information using multi task learning for speaker verification and diarization

Deep speaker embeddings have become the leading method for encoding spea...

A bridge between features and evidence for binary attribute-driven perfect privacy

Attribute-driven privacy aims to conceal a single user's attribute, cont...

An Attribute-Aligned Strategy for Learning Speech Representation

Advancement in speech technology has brought convenience to our life. Ho...

Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?

Automatic speech recognition (ASR) is a key technology in many services ...

Towards End-to-End Private Automatic Speaker Recognition

The development of privacy-preserving automatic speaker verification sys...

Improving on-device speaker verification using federated learning with privacy

Information on speaker characteristics can be useful as side information...

Topology of Privacy: Lattice Structures and Information Bubbles for Inference and Obfuscation

Information has intrinsic geometric and topological structure, arising f...