A comparative study of speech anonymization metrics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

A comparative study of speech anonymization metrics


Speech anonymization techniques have recently been proposed for preserving speakers' privacy. They aim at concealing speak-ers' identities while preserving the spoken content. In this study, we compare three metrics proposed in the literature to assess the level of privacy achieved. We exhibit through simulation the differences and blindspots of some metrics. In addition, we conduct experiments on real data and state-of-the-art anonymiza-tion techniques to study how they behave in a practical scenario. We show that the application-independent log-likelihood-ratio cost function C min llr provides a more robust evaluation of privacy than the equal error rate (EER), and that detection-based metrics provide different information from linkability metrics. Interestingly , the results on real data indicate that current anonymiza-tion design choices do not induce a regime where the differences between those metrics become apparent.
Fichier principal
Vignette du fichier
anonymization_metrics_IS2020.pdf (318.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02907918 , version 1 (28-07-2020)


  • HAL Id : hal-02907918 , version 1


Mohamed Maouche, Brij Mohan Lal Srivastava, Nathalie Vauquier, Aurélien Bellet, Marc Tommasi, et al.. A comparative study of speech anonymization metrics. INTERSPEECH 2020, Oct 2020, Shanghai, China. ⟨hal-02907918⟩
505 View
853 Download


Gmail Facebook Twitter LinkedIn More