cs.SDEmpirical

Layer-Wise Decision Fusion for Fake Audio Detection Using XLS-R

Jul 22, 2026

AI Summaryllama-3.1-8b-instruct

This paper proposes a novel layer-wise decision fusion method for fake audio detection using deep speech models, achieving the best cross-dataset performance.

Introduced a novel layer-wise decision fusion method for fake audio detection, which outperforms existing methods.

Keywords

fake audio detection deep learning speech models decision fusion

Before reading this…

Understanding of deep learning models Familiarity with audio forensics

Applications

→Audio forensics
→Speech recognition

Skill Ladder

To understand this paper, make sure you know these concepts first:

Understanding of deep learning modelsfind papers →
Familiarity with audio forensicsfind papers →

Abstract

More Like This

Recent fake audio detection methods often leverage large speech models to achieve robust speech representations. These models are typically very deep, providing multiple layer-wise representations. However, current works often rely solely on single layer representation or feature fusion to extract one utterance-level representation for decision making. These methods risk underutilizing rich information from multiple layers and might induce feature collapse. We propose a novel layer-wise decision fusion method that applies fusion after per-layer decision making and achieves the best cross-dataset performance on In-the-Wild dataset (EER 6.90%) compared to other strong baselines. Our model design also makes the model more transparent, allowing us to conduct detailed analysis to reveal the underlying mechanism of decision making.