Log In Sign Up

Speaker De-identification System using Autoencodersand Adversarial Training

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.


page 1

page 2

page 3

page 4


DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversion

The widespread adoption of speech-based online services raises security ...

Speaker Anonymization Using X-vector and Neural Waveform Models

The social media revolution has produced a plethora of web services to w...

Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training

The scarcity of training data and the large speaker variation in dysarth...

Privacy-Utility Balanced Voice De-Identification Using Adversarial Examples

Faced with the threat of identity leakage during voice data publishing, ...

Improving speaker de-identification with functional data analysis of f0 trajectories

Due to a constantly increasing amount of speech data that is stored in d...

Speaker Identification Experiments Under Gender De-Identification

The present work is based on the COST Action IC1206 for De-identificatio...

Digital Speech Algorithms for Speaker De-Identification

The present work is based on the COST Action IC1206 for De-identificatio...