Trusted Fake Audio Detection Based on Dirichlet Distribution

TL;DR

This paper introduces a fake audio detection method that models decision trustworthiness using the Dirichlet distribution, improving reliability and robustness in identifying fake speech across multiple datasets.

Contribution

The paper proposes a novel fake audio detection approach that incorporates Dirichlet distribution to model uncertainty and trustworthiness of model decisions.

Findings

High accuracy on ASVspoof datasets

Enhanced robustness against various attacks

Improved trustworthiness of detection decisions

Abstract

With the continuous development of deep learning-based speech conversion and speech synthesis technologies, the cybersecurity problem posed by fake audio has become increasingly serious. Previously proposed models for defending against fake audio have attained remarkable performance. However, they all fall short in modeling the trustworthiness of the decisions made by the models themselves. Based on this, we put forward a plausible fake audio detection approach based on the Dirichlet distribution with the aim of enhancing the reliability of fake audio detection. Specifically, we first generate evidence through a neural network. Uncertainty is then modeled using the Dirichlet distribution. By modeling the belief distribution with the parameters of the Dirichlet distribution, an estimate of uncertainty can be obtained for each decision. Finally, the predicted probabilities and corresponding uncertainty estimates are combined to form the final opinion. On the ASVspoof series dataset (i.e., ASVspoof 2019 LA, ASVspoof 2021 LA, and DF), we conduct a number of comparison experiments to verify the excellent performance of the proposed model in terms of accuracy, robustness, and trustworthiness.