Evaluating X-vector-based Speaker Anonymization under White-box Assessment - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Evaluating X-vector-based Speaker Anonymization under White-box Assessment

Abstract

In the scenario of the Voice Privacy challenge, anonymization is achieved by converting all utterances from a source speaker to match the same target identity; this identity being randomly selected. In this context, an attacker with maximum knowledge about the anonymization system can not infer the target identity. This article proposed to constrain the target selection to a specific identity, i.e., removing the random selection of identity, to evaluate the extreme threat under a whitebox assessment (the attacker has complete knowledge about the system). Targeting a unique identity also allows us to investigate whether some target's identities are better than others to anonymize a given speaker.
Fichier principal
Vignette du fichier
main.pdf (3 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03351943 , version 1 (23-09-2021)
hal-03351943 , version 2 (28-09-2021)
hal-03351943 , version 3 (29-09-2021)

Identifiers

Cite

Pierre Champion, Denis Jouvet, Anthony Larcher. Evaluating X-vector-based Speaker Anonymization under White-box Assessment. SPECOM 2021 - 23rd International Conference on Speech and Computer, Sep 2021, Saint Petersburg, Russia. ⟨hal-03351943v3⟩
126 View
127 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More