Whisper解释性更好用了
Transformer ASR模型如Whisper预测难解释。LEAF-X框架结合熵引导注意力加权、多层注意力展开和因果消融，定位低熵高影响头与层，生成稀疏token-帧归因。相比扰动解释器或原始注意力图，LEAF-X更好反映模型计算，忠诚度提升32%，局部性/稀疏性增强35-39%，归因最稳定。
Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models
Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret. Existing explainable AI (XAI) methods often lack faithfulness and precise temporal grounding. We propose Listening with Entropy-guided Attention for Faithful explainability (LEAF-X), a model-intrinsic XAI framework for transformer-based ASR. LEAF-X combines entropy-guided attention weighting, multi-layer attention rollout, and optional causal ablations to identify low-entropy, high-impact heads and layers, producing sparse token-to-frame attributions. Unlike perturbation-based explainers or raw attention maps, LEAF-X exploits the internal structure of encoder-decoder and speech-augmented decoder-only models to generate explanations that better reflect model computation. Results show 32% improved faithfulness, 35-39% stronger locality/sparsity, and the most stable attributions, supporting more transparent and auditable ASR.