VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research

TL;DR

VoicePAT is an open-source, modular toolkit that streamlines the evaluation of speaker anonymization methods, significantly reducing computation time and enhancing comparability in voice privacy research.

Contribution

The paper introduces a flexible, Python-based framework for speaker anonymization evaluation, with improved metrics and reduced computational costs, facilitating research progress.

Findings

Framework reduces evaluation time by up to 95%.

Modular design enables easy integration of different anonymization techniques.

Open-source code promotes wider adoption and reproducibility.

Abstract

Speaker anonymization is the task of modifying a speech recording such that the original speaker cannot be identified anymore. Since the first Voice Privacy Challenge in 2020, along with the release of a framework, the popularity of this research topic is continually increasing. However, the comparison and combination of different anonymization approaches remains challenging due to the complexity of evaluation and the absence of user-friendly research frameworks. We therefore propose an efficient speaker anonymization and evaluation framework based on a modular and easily extendable structure, almost fully in Python. The framework facilitates the orchestration of several anonymization approaches in parallel and allows for interfacing between different techniques. Furthermore, we propose modifications to common evaluation methods which improves the quality of the evaluation and reduces their computation time by 65 to 95%, depending on the metric. Our code is fully open source.