2024/06/10 by Yujie Chen, Chen, Yujie, Jiangyan Yi +17 · 14 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Digital Media Forensic Detection #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2406.06086
openalex publication_date 2024/06/10 · openalex created_date 2024/06/12 · openalex updated_date 2026/08/01
Fake artefacts for discriminating between bonafide and fake audio can exist in both short- and long-range segments. Therefore, combining local and global feature information can effectively discriminate between bonafide and fake audio. This paper proposes an end-to-end bidirectional state space model, named RawBMamba, to capture both short- and long-range discriminative information for audio deepfake detection. Specifically, we use sinc Layer and multiple convolutional layers to capture short-range features, and then design a bidirectional Mamba to address Mamba's unidirectional modelling problem and further capture long-range feature information. Moreover, we develop a bidirectional fusion module to integrate embeddings, enhancing audio context representation and combining short- and long-range information. The results show that our proposed RawBMamba achieves a 34.1% improvement over Rawformer on ASVspoof2021 LA dataset, and demonstrates competitive performance on other datasets.