Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck

TL;DR

This paper introduces a transfer learning approach using wav2vec 2.0 with variational information bottleneck to enhance anti-spoofing in speaker verification, especially for unseen and low-resource scenarios.

Contribution

It presents a novel transfer learning scheme with VIB for speech anti-spoofing, improving generalization and robustness over existing methods.

Findings

Outperforms state-of-the-art anti-spoofing systems on ASVspoof 2019 LA database.

Enhances detection in low-resource and cross-dataset settings.

Demonstrates robustness to data size and distribution variations.

Abstract

Recent advances in sophisticated synthetic speech generated from text-to-speech (TTS) or voice conversion (VC) systems cause threats to the existing automatic speaker verification (ASV) systems. Since such synthetic speech is generated from diverse algorithms, generalization ability with using limited training data is indispensable for a robust anti-spoofing system. In this work, we propose a transfer learning scheme based on the wav2vec 2.0 pretrained model with variational information bottleneck (VIB) for speech anti-spoofing task. Evaluation on the ASVspoof 2019 logical access (LA) database shows that our method improves the performance of distinguishing unseen spoofed and genuine speech, outperforming current state-of-the-art anti-spoofing systems. Furthermore, we show that the proposed system improves performance in low-resource and cross-dataset settings of anti-spoofing task significantly, demonstrating that our system is also robust in terms of data size and data distribution.