TO-Rawnet: Improving RawNet with TCN and Orthogonal Regularization for Fake Audio Detection

TL;DR

This paper enhances RawNet for fake audio detection by integrating orthogonal regularization and TCN, significantly improving performance by reducing error rates on the ASVspoof 2019 dataset.

Contribution

It introduces orthogonal convolution and TCN into RawNet, optimizing filter independence and capturing long-term speech dependencies for better detection accuracy.

Findings

66.09% relative reduction in EER on logical access scenario

Effective in detecting fake audio attacks

Improved discriminability of features

Abstract

Current fake audio detection relies on hand-crafted features, which lose information during extraction. To overcome this, recent studies use direct feature extraction from raw audio signals. For example, RawNet is one of the representative works in end-to-end fake audio detection. However, existing work on RawNet does not optimize the parameters of the Sinc-conv during training, which limited its performance. In this paper, we propose to incorporate orthogonal convolution into RawNet, which reduces the correlation between filters when optimizing the parameters of Sinc-conv, thus improving discriminability. Additionally, we introduce temporal convolutional networks (TCN) to capture long-term dependencies in speech signals. Experiments on the ASVspoof 2019 show that the Our TO-RawNet system can relatively reduce EER by 66.09\% on logical access scenario compared with the RawNet, demonstrating its effectiveness in detecting fake audio attacks.