Learning From Yourself: A Self-Distillation Method for Fake Speech Detection

TL;DR

This paper introduces a self-distillation approach for fake speech detection that enhances shallow network performance by leveraging a deep network as a teacher, improving accuracy without increasing model complexity.

Contribution

The novel self-distillation method uses the deepest network to guide shallow networks, effectively capturing fine-grained speech features for improved fake speech detection.

Findings

Significant accuracy improvements on ASVspoof datasets

Effective enhancement of shallow networks without added complexity

Demonstrated superiority over baseline models

Abstract

In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very important, such as spectrogram defects, mute segments, and so on, which are often perceived by shallow networks. However, shallow networks have much noise, which can not capture this very well. To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks. Specifically, the networks of FSD are divided into several segments, the deepest network being used as the teacher model, and all shallow networks become multiple student models by adding classifiers. Meanwhile, the distillation path between the deepest network feature and shallow network features is used to reduce the feature difference. A series of experimental results on the ASVspoof 2019 LA and PA datasets show the effectiveness of the proposed method, with significant improvements compared to the baseline.