Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning

TL;DR

This paper presents a novel anti-spoofing method for speaker verification that combines a simple attention module, joint optimization with additive angular margin loss, and meta-learning to improve robustness against unseen attacks, achieving state-of-the-art results.

Contribution

It introduces a simple attention mechanism and a joint optimization framework with meta-learning for enhanced anti-spoofing performance and generalization.

Findings

Achieved a pooled EER of 0.99%.

Achieved a min t-DCF of 0.0289.

Outperformed current state-of-the-art systems.

Abstract

Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks. This study introduces a simple attention module to infer 3-dim attention weights for the feature map in a convolutional layer, which then optimizes an energy function to determine each neuron's importance. With the advancement of both voice conversion and speech synthesis technologies, unseen spoofing attacks are constantly emerging to limit spoofing detection system performance. Here, we propose a joint optimization approach based on the weighted additive angular margin loss for binary classification, with a meta-learning training framework to develop an efficient system that is robust to a wide range of spoofing attacks for model generalization enhancement. As a result, when compared to current state-of-the-art systems, our proposed approach delivers a competitive result with a pooled EER of 0.99% and min t-DCF of 0.0289.