A Study of F0 Modification for X-Vector Based Speech Pseudo-Anonymization Across Gender

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

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
2 LIUM - Laboratoire d'Informatique de l'Université du Mans

Speech pseudo-anonymization aims at altering a speech signal to map the identifiable personal characteristics of a given speaker to another identity. In other words, it aims to hide the source speaker identity while preserving the intelligibility of the spoken content. This study takes place in the VoicePrivacy 2020 challenge framework, where the baseline system performs pseudo-anonymization by modifying x-vector information to match a target speaker while keeping the fundamental frequency (F0) unchanged. We propose to alter other paralin-guistic features, here F0, and analyze the impact of this modification across gender. We found that the proposed F0 modification always improves pseudo-anonymization. We observed that both source and target speaker genders affect the performance gain when modifying the F0.

Mots clés: VoicePrivacy 2020 Challenge; Speaker anonymization; F0 modification

Domaines: Informatique [cs]; Traitement du signal et de l'image [eess.SP]

Pierre Champion, Denis Jouvet, Anthony Larcher. A Study of F0 Modification for X-Vector Based Speech Pseudo-Anonymization Across Gender. [Research Report] INRIA Nancy, équipe Multispeech. 2020. ⟨hal-02995862v1⟩