一作ACL 2026Findings· Findings of ACL
XLSR - M am B o: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection
Kwok-Ho Ng · Tingting Song · Yongdong WU · Zhihua Xia
摘要
Advanced speech synthesis technologies have enabled highly realistic speech generation, posing security risks that motivate research into audio deepfake detection (ADD). While state space models (SSMs) offer linear complexity, pure causal SSMs architectures often struggle with the content-based r...