Self-supervised pre-training with acoustic configurations for replay spoofing detection

TL;DR

This paper introduces a self-supervised pretraining method for replay spoofing detection that leverages acoustic configurations from existing datasets, improving detection accuracy without extensive physical data collection.

Contribution

It proposes a novel self-supervised framework focusing on acoustic configurations, enabling effective pretraining for replay spoofing detection using datasets from related tasks.

Findings

Outperforms baseline by 30% in detection accuracy

Effective use of existing datasets for pretraining

Improves robustness in replay spoofing detection

Abstract

Constructing a dataset for replay spoofing detection requires a physical process of playing an utterance and re-recording it, presenting a challenge to the collection of large-scale datasets. In this study, we propose a self-supervised framework for pretraining acoustic configurations using datasets published for other tasks, such as speaker verification. Here, acoustic configurations refer to the environmental factors generated during the process of voice recording but not the voice itself, including microphone types, place and ambient noise levels. Specifically, we select pairs of segments from utterances and train deep neural networks to determine whether the acoustic configurations of the two segments are identical. We validate the effectiveness of the proposed method based on the ASVspoof 2019 physical access dataset utilizing two well-performing systems. The experimental results demonstrate that the proposed method outperforms the baseline approach by 30%.