Local density-based score normalization is an effective component of distance-based embedding methods for anomalous sound detection, particularly when data densities vary across conditions or domains. In practice, however, performance depends strongly on neighborhood size. Increasing it can degrade detection accuracy when neighborhood expansion crosses cluster boundaries, violating the locality assumption of local density estimation. This observation motivates adapting the neighborhood size based on locality preservation rather than fixing it in advance. We realize this by proposing cluster exit detection, a lightweight mechanism that identifies distance discontinuities and selects neighborhood sizes accordingly. Experiments across multiple embedding models and datasets show improved robustness to neighborhood-size selection and consistent performance gains.

翻译：基于局部密度的分数归一化是基于距离的嵌入方法在异常声音检测中的有效组成部分，尤其在数据密度随条件或领域变化时。然而，在实践中，其性能高度依赖于邻域大小。当邻域扩展跨越聚类边界时，增加邻域大小可能降低检测精度，这违反了局部密度估计的局部性假设。这一观察结果促使我们基于局部性保持来调整邻域大小，而非预先固定。我们通过提出聚类退出检测来实现这一目标，这是一种轻量级机制，可识别距离不连续性并据此选择邻域大小。在多种嵌入模型和数据集上的实验表明，该方法提高了对邻域大小选择的鲁棒性，并获得了持续的性能提升。