Evaluating Voice Conversion-based Privacy Protection against Informed Attackers

Srivastava, Brij Mohan Lal; Vauquier, Nathalie; Sahidullah, Md; Bellet, Aurelien; Tommasi, Marc; Vincent, Emmanuel

Document type :

Communication dans un congrès avec actes

Title :

Evaluating Voice Conversion-based Privacy Protection against Informed Attackers

Author(s) :

Srivastava, Brij Mohan Lal [Auteur]
Machine Learning in Information Networks [MAGNET]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]
Vauquier, Nathalie [Auteur]
Machine Learning in Information Networks [MAGNET]
Sahidullah, Md [Auteur]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]
Bellet, Aurelien [Auteur]

Machine Learning in Information Networks [MAGNET]
Tommasi, Marc [Auteur]

Machine Learning in Information Networks [MAGNET]
Vincent, Emmanuel [Auteur]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]

Conference title :

ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing

Conference organizers(s) :

IEEE Signal Processing Society

City :

Barcelona

Country :

Espagne

Start date of the conference :

2020-05-04

Publication date :

2020-05-04

English keyword(s) :

linkage attack
privacy
speaker verification
attacker
speech recognition
voice conversion

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Informatique et langage [cs.CL]

English abstract : [en]

Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymization ...
Show more >Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymization aims to make the data unlinkable, i.e., ensure that no utterance can be linked to its original speaker. In this paper, we investigate anonymization methods based on voice conversion. In contrast to prior work, we argue that various linkage attacks can be designed depending on the attackers' knowledge about the anonymization scheme. We compare two frequency warping-based conversion methods and a deep learning based method in three attack scenarios. The utility of converted speech is measured via the word error rate achieved by automatic speech recognition, while privacy protection is assessed by the increase in equal error rate achieved by state-of-the-art i-vector or x-vector based speaker verification. Our results show that voice conversion schemes are unable to effectively protect against an attacker that has extensive knowledge of the type of conversion and how it has been applied, but may provide some protection against less knowledgeable attackers.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Apprentissage distribué, personnalisé, préservant la privacité pour le traitement de la parole

Collections :