Speaker De-identification System using Autoencoders and Adversarial Training

TL;DR

This paper presents a novel speaker de-identification system using autoencoders and adversarial training to enhance speech privacy by reducing speaker and demographic information while maintaining speech intelligibility.

Contribution

The proposed system combines autoencoders with adversarial training to effectively suppress speaker, gender, and accent features in speech data, improving privacy protection.

Findings

Increased equal error rate in speaker verification

Maintained speech intelligibility after anonymization

Effective suppression of demographic speech features

Abstract

The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice assistants empowered by the vertiginous breakthroughs in Deep Learning are prompting important concerns in the European Union to preserve speech data privacy. For instance, an attacker can record speech from users and impersonate them to get access to systems requiring voice identification. Hacking speaker profiles from users is also possible by means of existing technology to extract speaker, linguistic (e.g., dialect) and paralinguistic features (e.g., age) from the speech signal. In order to mitigate these weaknesses, in this paper, we propose a speaker de-identification system based on adversarial training and autoencoders in order to suppress speaker, gender, and accent information from speech. Experimental results show that combining adversarial learning and autoencoders increase the equal error rate of a speaker verification system while preserving the intelligibility of the anonymized spoken content.