# MemNMF: Memory-Augmented NMF on LPC Spectra for Anomalous Sound Detection

arXiv: https://arxiv.org/abs/2607.22086 · HTML: https://mlsanity.com/paper/2607.22086/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Understanding Batch Normalization](https://mlsanity.com/paper/1806.02375/) (2018)
- [MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection](https://mlsanity.com/paper/1909.09347/) (2019)
- [ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection](https://mlsanity.com/paper/1908.03299/) (2019)
- [Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring](https://mlsanity.com/paper/2006.05822/) (2020)
- [Anomalous sound detection based on interpolation deep neural network](https://mlsanity.com/paper/2005.09234/) (2020)
- [First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline](https://mlsanity.com/paper/2303.00455/) (2023)
- [Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection](https://mlsanity.com/paper/2305.12111/) (2023)
- [Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space](https://mlsanity.com/paper/2202.13245/) (2022)

## Abstract (arXiv)

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.