SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
This addresses the challenge of detecting forged face videos, particularly for unseen datasets and perturbations, which is crucial for digital forensics applications.
The paper tackles face forgery detection by leveraging audio-visual speech representation learning, achieving state-of-the-art performance in cross-dataset generalization and robustness without using fake videos in training.
Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In this paper, we tackle this issue by leveraging the synergy between audio and visual speech elements, embarking on a novel approach through audio-visual speech representation learning. Our work is motivated by the finding that audio signals, enriched with speech content, can provide precise information effectively reflecting facial movements. To this end, we first learn precise audio-visual speech representations on real videos via a self-supervised masked prediction task, which encodes both local and global semantic information simultaneously. Then, the derived model is directly transferred to the forgery detection task. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of cross-dataset generalization and robustness, without the participation of any fake video in model training. Code is available at https://github.com/Eleven4AI/SpeechForensics.