2 papers
cs.SD2025
FakeSound2: A Benchmark for Explainable and Generalizable Deepfake Sound Detection
Zeyu Xie, Yaoyun Zhang, Xuenan Xu +4
The rapid development of generative audio raises ethical and security concerns stemming from forged data, making deepfake sound detection an important safeguard against the malicio…
cs.MM2023
AFL-Net: Integrating Audio, Facial, and Lip Modalities with a Two-step Cross-attention for Robust Speaker Diarization in the Wild
Yongkang Yin, Xu Li, Ying Shan +1
Speaker diarization in real-world videos presents significant challenges due to varying acoustic conditions, diverse scenes, the presence of off-screen speakers, etc. This paper bu…