BabelFake: A Multilingual Audio-Visual DeepFake Benchmark

arXiv:2610.06339 · cs.CV · Submitted 2026-10-05 · Read on arXiv

cs.CV

Submitted: 2026-10-05

Updated: 2026-10-08

Code: https://github.com/hacksider/Deep-Live-Cam

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• Deep Learning Models for Multilingual Hate Speech Detection
• MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark
• Qwen3-TTS Technical Report
• LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
• Fish Audio S2 Technical Report
• Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models