One-Class Knowledge Distillation for Spoofing Speech Detection

TL;DR

This paper proposes a one-class knowledge distillation approach for spoofing speech detection, enhancing generalization to unseen attacks by learning only from bonafide speech.

Contribution

It introduces a teacher-student framework to effectively train a one-class model for spoofing detection, outperforming existing methods.

Findings

Outperforms state-of-the-art methods on ASVspoof 21DF dataset

Demonstrates superior generalization on InTheWild dataset

Effective one-class training with teacher guidance

Abstract

The detection of spoofing speech generated by unseen algorithms remains an unresolved challenge. One reason for the lack of generalization ability is traditional detecting systems follow the binary classification paradigm, which inherently assumes the possession of prior knowledge of spoofing speech. One-class methods attempt to learn the distribution of bonafide speech and are inherently suited to the task where spoofing speech exhibits significant differences. However, training a one-class system using only bonafide speech is challenging. In this paper, we introduce a teacher-student framework to provide guidance for the training of a one-class model. The proposed one-class knowledge distillation method outperforms other state-of-the-art methods on the ASVspoof 21DF dataset and InTheWild dataset, which demonstrates its superior generalization ability.