Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding

TL;DR

This paper introduces a novel asynchronous voice anonymization method that uses adversarial perturbation on speaker embeddings to obscure speaker identity from machine recognition while maintaining human perception.

Contribution

It proposes a speaker disentanglement framework with adversarial perturbation for voice anonymization, balancing privacy and perceptual quality, which is a new approach in the field.

Findings

Speaker attributes were obscured in 60.71% of utterances.

The method effectively balances anonymization and human perception.

Experiments on LibriSpeech dataset validate the approach.

Abstract

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and human perception. In this paper, we focus on altering the voice attributes against machine recognition while retaining human perception. We referred to this as the asynchronous voice anonymization. To this end, a speech generation framework incorporating a speaker disentanglement mechanism is employed to generate the anonymized speech. The speaker attributes are altered through adversarial perturbation applied on the speaker embedding, while human perception is preserved by controlling the intensity of perturbation. Experiments conducted on the LibriSpeech dataset showed that the speaker attributes were obscured with their human perception preserved for 60.71% of the processed utterances.