Replay spoofing detection system for automatic speaker verification using multi-task learning of noise classes

TL;DR

This paper introduces a replay spoofing detection system for automatic speaker verification that leverages multi-task learning to classify noise types and improve detection accuracy, showing a 30% relative performance boost.

Contribution

The novel approach combines replay attack detection with noise classification in a multi-task learning framework, enhancing detection performance.

Findings

30% relative improvement on evaluation set

Effective multi-task learning of noise and spoofing detection

Improved robustness against replay attacks

Abstract

In this paper, we propose a replay attack spoofing detection system for automatic speaker verification using multitask learning of noise classes. We define the noise that is caused by the replay attack as replay noise. We explore the effectiveness of training a deep neural network simultaneously for replay attack spoofing detection and replay noise classification. The multi-task learning includes classifying the noise of playback devices, recording environments, and recording devices as well as the spoofing detection. Each of the three types of the noise classes also includes a genuine class. The experiment results on the ASVspoof2017 datasets demonstrate that the performance of our proposed system is improved by 30% relatively on the evaluation set.