Probing the Feasibility of Multilingual Speaker Anonymization

TL;DR

This paper explores extending multilingual speaker anonymization technology beyond English, demonstrating its effectiveness across nine languages and highlighting the importance of speech synthesis quality for privacy protection.

Contribution

It introduces a multilingual extension of a speaker anonymization system, enabling privacy preservation across nine languages using language-independent speaker embeddings.

Findings

Successful anonymization across nine languages.

Speaker embeddings trained on English generalize to other languages.

Speech synthesis quality impacts anonymization effectiveness.

Abstract

In speaker anonymization, speech recordings are modified in a way that the identity of the speaker remains hidden. While this technology could help to protect the privacy of individuals around the globe, current research restricts this by focusing almost exclusively on English data. In this study, we extend a state-of-the-art anonymization system to nine languages by transforming language-dependent components to their multilingual counterparts. Experiments testing the robustness of the anonymized speech against privacy attacks and speech deterioration show an overall success of this system for all languages. The results suggest that speaker embeddings trained on English data can be applied across languages, and that the anonymization performance for a language is mainly affected by the quality of the speech synthesis component used for it.