Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation

Driss Matrouf
Andreas Nautsch
  • Function : Author
  • PersonId : 1077079

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.
Fichier principal
Vignette du fichier
adv_sex_disentanglement_IS2021(3).pdf (277.04 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03046920 , version 1 (08-12-2020)
hal-03046920 , version 2 (23-04-2021)
hal-03046920 , version 3 (16-06-2021)

Identifiers

  • HAL Id : hal-03046920 , version 3

Cite

Paul-Gauthier Noé, Mohammad Mohammadamini, Driss Matrouf, Titouan Parcollet, Andreas Nautsch, et al.. Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation. Interspeech 2021, Aug 2021, Brno, Czech Republic. ⟨hal-03046920v3⟩

Collections

UNIV-AVIGNON LIA
194 View
217 Download

Share

Gmail Facebook X LinkedIn More