Probing the Feasibility of Multilingual Speaker Anonymization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meyer, Sarina, Lux, Florian, Vu, Ngoc Thang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916425066610688
author Meyer, Sarina
Lux, Florian
Vu, Ngoc Thang
author_facet Meyer, Sarina
Lux, Florian
Vu, Ngoc Thang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02937
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Probing the Feasibility of Multilingual Speaker Anonymization
Meyer, Sarina
Lux, Florian
Vu, Ngoc Thang
Computation and Language
Sound
Audio and Speech Processing
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.
title Probing the Feasibility of Multilingual Speaker Anonymization
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2407.02937