SIGNL: A Label-Efficient Audio Deepfake Detection System via Spectral-Temporal Graph Non-Contrastive Learning

TL;DR

SIGNL introduces a spectral-temporal graph non-contrastive learning framework that efficiently detects audio deepfakes using minimal labeled data, leveraging structured spectral-temporal representations for improved accuracy and generalization.

Contribution

The paper presents a novel dual-view graph modeling approach for audio deepfake detection, combining spectral and temporal graphs with non-contrastive self-supervised learning.

Findings

Achieves 7.88% EER on ASVspoof 2021 DF with minimal labeled data.

Outperforms existing methods on multiple benchmarks.

Generalizes well to unseen conditions, demonstrating robustness.

Abstract

Audio deepfake detection is increasingly important as synthetic speech becomes more realistic and accessible. Recent methods, including those using graph neural networks (GNNs) to model frequency and temporal dependencies, show strong potential but need large amounts of labeled data, which limits their practical use. Label-efficient alternatives like graph-based non-contrastive learning offer a potential solution, as they can learn useful representations from unlabeled data without using negative samples. However, current graph non-contrastive approaches are built for single-view graph representations and cannot be directly used for audio, which has unique spectral and temporal structures. Bridging this gap requires dual-view graph modeling suited to audio signals. In this work, we introduce SIGNL (Spectral-temporal vIsion Graph Non-contrastive Learning), a label-efficient expert system for detecting audio deepfakes. SIGNL operates on the visual representation of audio, such as spectrograms or other time-frequency encodings, transforming them into spectral and temporal graphs for structured feature extraction. It then employs graph convolutional encoders to learn complementary frequency-time features, effectively capturing the unique characteristics of audio. These encoders are pre-trained using a non-contrastive self-supervised learning strategy on augmented graph pairs, enabling effective representation learning without labeled data. The resulting encoders are then fine-tuned on minimal labelled data for downstream deepfake detection. SIGNL achieves strong performance on multiple audio deepfake detection benchmarks, including 7.88% EER on ASVspoof 2021 DF and 3.95% EER on ASVspoof 5 using only 5% labeled data. It also generalizes well to unseen conditions, reaching 10.16% EER on the In-The-Wild dataset when trained on CFAD.