Preprint
Aug 2026
Textual Acoustic Grounding for Generalizable LLM-Based Deepfake Voice Detection
Deepfake voice detection suffers from poor generalization across unseen domains. While Audio Large Language Models (ALLMs) show promise, the modality gap between continuous audio embeddings which capture the subtle acoustic details necessary for deepfake detection and the semantic space of LLMs remains a critical, unde...
Yassine El Kheir, Xin Wang, Wanying Ge et al.
· 1 citation