A Study On Data Augmentation In Voice Anti-Spoofing

TL;DR

This paper investigates data augmentation techniques to enhance the detection of synthetic or spoofed audio, introducing novel methods like SpecAverage and a new spectrogram feature design, achieving state-of-the-art results in anti-spoofing challenges.

Contribution

It presents new data augmentation strategies, including compression, channel augmentation, and SpecAverage, along with a novel spectrogram feature design, significantly improving anti-spoofing system performance.

Findings

State-of-the-art EER of 15.46% in Deep Fake detection

50% reduction in baseline EER for Logical Access

Improved generalization through SpecAverage augmentation

Abstract

In this paper, we perform an in-depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different band-widths, and unseen spoofing attacks, which have all been shown to significantly degrade the performance of audio-based systems and Anti-Spoofing systems. Our results are based on the ASVspoof 2021 challenge, in the Logical Access (LA) and Deep Fake (DF) categories. Our study is Data-Centric, meaning that the models are fixed and we significantly improve the results by making changes in the data. We introduce two forms of data augmentation - compression augmentation for the DF part, compression & channel augmentation for the LA part. In addition, a new type of online data augmentation, SpecAverage, is introduced in which the audio features are masked with their average value in order to improve generalization. Furthermore, we introduce a Log spectrogram feature design that improved the results. Our best single system and fusion scheme both achieve state-of-the-art performance in the DF category, with an EER of 15.46% and 14.46% respectively. Our best system for the LA task reduced the best baseline EER by 50% and the min t-DCF by 16%. Our techniques to deal with spoofed data from a wide variety of distributions can be replicated and can help anti-spoofing and speech-based systems enhance their results.