Explainable AI (XAI) is commonly applied to anomalous sound detection (ASD) models to identify which time-frequency regions of an audio signal contribute to an anomaly decision. However, most audio explanations rely on qualitative inspection of saliency maps, leaving open the question of whether these attributions accurately reflect the spectral cues the model uses. In this work, we introduce a new quantitative framework for evaluating XAI faithfulness in machine-sound analysis by directly linking attribution relevance to model behaviour through systematic frequency-band removal. This approach provides an objective measure of whether an XAI method for machine ASD correctly identifies frequency regions that influence an ASD model's predictions. By using four widely adopted methods, namely Integrated Gradients, Occlusion, Grad-CAM and SmoothGrad, we show that XAI techniques differ in reliability, with Occlusion demonstrating the strongest alignment with true model sensitivity and gradient-+based methods often failing to accurately capture spectral dependencies. The proposed framework offers a reproducible way to benchmark audio explanations and enables more trustworthy interpretation of spectrogram-based ASD systems.

翻译：可解释人工智能（XAI）常被应用于异常声音检测（ASD）模型，以识别音频信号的哪些时频区域对异常判定产生影响。然而，大多数音频解释依赖于对显著性图的定性检查，这些归因是否准确反映模型所使用的频谱线索仍存疑问。本研究通过系统性的频带移除将归因相关性与模型行为直接关联，提出一种用于评估机器声音分析中XAI忠实性的定量框架。该方法为机器ASD的XAI方法能否正确识别影响ASD模型预测的频率区域提供了客观度量。通过采用四种广泛使用的方法——积分梯度、遮挡法、Grad-CAM与SmoothGrad，我们发现XAI技术的可靠性存在差异：遮挡法与真实模型敏感度的吻合度最高，而基于梯度的方法往往无法准确捕捉频谱依赖性。所提出的框架为音频解释提供了可复现的基准测试方法，并增强了对基于频谱图的ASD系统的可信解释能力。