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

Pierre Champion (1) , Denis Jouvet (1) , Anthony Larcher (2)

1 Inria - Institut National de Recherche en Informatique et en Automatique
2 LIUM - Laboratoire d'Informatique de l'Université du Mans

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.

Mots clés: Speaker anonymization; VoicePrivacy; Anonymization evaluation

Domaines: Intelligence artificielle [cs.AI]

Pierre Champion, Denis Jouvet, Anthony Larcher. Evaluating X-vector-based Speaker Anonymization under White-box Assessment. 23rd International Conference on Speech and Computer - SPECOM 2021, Sep 2021, Saint Petersburg, Russia. ⟨hal-03351943v1⟩