In-the-Wild

The 'In-the-Wild' dataset/benchmark contains real-world audio recordings used to evaluate the performance of audio deepfake detection methods under variable conditions.

Papers using In-the-Wild (13)

Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative2025 · 6 citesGeneralizable Audio Deepfake Detection via Latent Space Refinement and Augmentation2025 · 6 citesGeneralizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment2025 · 1 citesWST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection2026Reliable Audio Deepfake Detection in Variable Conditions via Quantum-Kernel SVMs2025QAMO: Quality-aware Multi-centroid One-class Learning For Speech Deepfake Detection2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing2025XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection2024A robust audio deepfake detection system via multi-view feature2024 · 45 citesCan large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?2023 · 2 citesCompression Robust Synthetic Speech Detection Using Patched Spectrogram Transformer2024 · 2 citesHeterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake2024Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge2024