BreathNet: Generalizable Audio Deepfake Detection via Breath-Cue-Guided Feature Refinement

TL;DR

BreathNet is a novel deepfake audio detection framework that leverages fine-grained breath cues and spectral features, combined with specialized loss functions, to achieve state-of-the-art generalization across multiple benchmarks.

Contribution

The paper introduces BreathNet, integrating breath-related cues via BreathFiLM and a fusion of temporal and spectral features, along with a new set of feature losses for improved deepfake detection.

Findings

Achieves 1.99% average EER on four benchmarks.

Outperforms existing methods on the In-the-Wild dataset.

Attains 4.94% EER on the latest ASVspoof5 benchmark.

Abstract

As deepfake audio becomes more realistic and diverse, developing generalizable countermeasure systems has become crucial. Existing detection methods primarily depend on XLS-R front-end features to improve generalization. Nonetheless, their performance remains limited, partly due to insufficient attention to fine-grained information, such as physiological cues or frequency-domain features. In this paper, we propose BreathNet, a novel audio deepfake detection framework that integrates fine-grained breath information to improve generalization. Specifically, we design BreathFiLM, a feature-wise linear modulation mechanism that selectively amplifies temporal representations based on the presence of breathing sounds. BreathFiLM is trained jointly with the XLS-R extractor, in turn encouraging the extractor to learn and encode breath-related cues into the temporal features. Then, we use the frequency front-end to extract spectral features, which are then fused with temporal features to provide complementary information introduced by vocoders or compression artifacts. Additionally, we propose a group of feature losses comprising Positive-only Supervised Contrastive Loss (PSCL), center loss, and contrast loss. These losses jointly enhance the discriminative ability, encouraging the model to separate bona fide and deepfake samples more effectively in the feature space. Extensive experiments on five benchmark datasets demonstrate state-of-the-art (SOTA) performance. Using the ASVspoof 2019 LA training set, our method attains 1.99% average EER across four related eval benchmarks, with particularly strong performance on the In-the-Wild dataset, where it achieves 4.70% EER. Moreover, under the ASVspoof5 evaluation protocol, our method achieves an EER of 4.94% on this latest benchmark.