用线性预测谱增强异常声音检测，提升噪声下的稳定性。
MemNMF: Memory-Augmented NMF on LPC Spectra for Anomalous Sound Detection
- 基于线性预测谱的内存增强稀疏分解方法
- 在多类设备上实现更优的异常检测性能
- 适合工业场景中复杂噪声环境下的故障监测
基于自编码器的异常声音检测在设备状态监控中具有吸引力，因其仅需正常样本训练，并可通过重构误差生成可解释的异常分数。以往工作多采用谱图自编码器，但重建精细时频模式对噪声和瞬态敏感，且部分异常输入可被良好重构，削弱了正常与异常的区分能力。本文提出MemNMF，一种在线性预测编码（LPC）谱上运行的约束重建方法，该谱是频谱包络的紧凑估计。MemNMF从正常LPC谱学习的NMF字典初始化记忆模块，将每个输入重构为原型正常谱模式的注意力加权组合。在MIMII和DCASE 2020 Task 2数据集上，针对多种设备类型和工况的实验表明，使用LPC谱输入可提升标准自编码器基线性能，而MemNMF进一步带来显著增益，尤其在噪声大、非平稳条件下表现突出。
原文摘要 · Abstract (English)
Autoencoder-based anomalous sound detection is attractive for machine condition monitoring because it can be trained using only normal recordings and yields an interpretable anomaly score from reconstruction error. Most prior work uses spectrogram autoencoders, but reconstructing detailed time--frequency patterns is sensitive to noise and transients, and models can reconstruct some anomalous inputs well, weakening normal--anomaly separation. We propose MemNMF, a constrained reconstruction method that operates on the Linear Predictive Coding spectrum, a compact estimate of the spectral envelope. MemNMF initializes a memory module from an NMF dictionary learned on normal LPC spectra and reconstructs each input as an attention-weighted combination of prototypical normal spectral patterns. Experiments on MIMII and DCASE 2020 Task 2 across multiple machine types and operating conditions show that LPC-spectrum inputs improve a standard autoencoder baseline and that MemNMF yields further gains, with especially strong robustness under noisy, non-stationary settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。