Anonymizing Speaker Voices: Easy to Imitate, Difficult to Recognize? - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Anonymizing Speaker Voices: Easy to Imitate, Difficult to Recognize?

Résumé

A vastly under-explored area in speech anonymization involves characterizing how different speakers perform in voice privacy tasks. In this paper, we present a deeper analysis by creating and analyzing groups of challenging speakers categorized based on their performance in two related facets of voice anonymization evaluation: (1) speaker similarity using automatic speaker verification(ASV) and (2) human perception using a large-scale A/B listening test. We group speakers into four categories (sheep, goats, lambs, and wolves) based on their anonymization properties. We present an extension of voice anonymization evaluation by identifying speakers who are easy to imitate or difficult to recognize. This knowledge is important for trustworthy anonymization evaluation, and it has the potential to influence how evaluation datasets are created from a pool of speakers. We provide further insights on speaker influence on anonymized speech between human perception and automatic speaker similarity scoring.
Fichier principal
Vignette du fichier
ANONYMIZING SPEAKER VOICES EASY TO IMITATE, DIFFICULT TO RECOGNIZE.pdf (756.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04527700 , version 1 (03-04-2024)

Licence

Paternité

Identifiants

Citer

Jennifer Williams, Karla Pizzi, Natalia Tomashenko, Sneha Das. Anonymizing Speaker Voices: Easy to Imitate, Difficult to Recognize?. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.12491-12495, ⟨10.1109/ICASSP48485.2024.10445935⟩. ⟨hal-04527700⟩
12 Consultations
9 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More