Skip to content

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

Jul 2026 · arXiv.org · Vol abs/2607.22086 · 0 citations · 29 references
Computer Science

TL;DR

MemNMF is proposed, a constrained reconstruction method that operates on the Linear Predictive Coding spectrum, a compact estimate of the spectral envelope that improves a standard autoencoder baseline and yields further gains, with especially strong robustness under noisy, non-stationary settings.

Abstract

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.

View source

Similar papers

Open access Sep 2026

Autoencoder-Based FM Spectrum Anomaly Detection: A Pipeline-Level Study of Preprocessing, Model Capacity, and Reconstruction Scoring

Reconstruction-based anomaly detection for real-world very-high-frequency very-high-frequency (VHF) Band II radio-broadcasting spectrum measurements using autoencoders whose gradient-based parameter optimization was performed exclusively on normal observations is investigated.

S. L. Takács, Konrád Kajdy · 0 citations

What Survives the Codec Shift: Pooled No-Vocals Residuals for Speech Deepfake Detection

The transition from vocoder-based to neural-codec speech synthesis makes generalization more difficult for speech deepfake detectors, particularly those relying on speech-oriented representations. It remains unclear which acoustic representations retain discriminative information when the generation mechanism changes....

Jia-Jun Xu, Meng-Lu Li, Xiao-Ping Zhang · 0 citations
Conference Aug 2026

On the Choice of Score Aggregation Functions for Anomalous Sound Detection

The standard autoencoder (AE) baseline for anomalous sound detection aggregates frame-level reconstruction errors by their mean, which can dilute localized anomalies in non-stationary machine sounds. We systematically compare four aggregation functions - mean, max, percentile-95, and variance - across all four machine...

Haruto Kuroda · 0 citations
Conference Open access Sep 2026

Few-Shot Adaptation for Anomalous Sound Detection at Low False-Positive Rate

Reliable fault detection is crucial for industrial machinery in large-scale facilities, where unexpected failures can cause costly downtime and production interruptions. Although acoustic monitoring provides a scalable solution for machine condition monitoring, its deployment is often constrained by high false-positive...

Simone Lugani, C. Pichler, H. Wegleiter et al. · 0 citations
Open access 2026

Memory-Augmented Autoencoder for Industrial Anomaly Detection

A Memory-Augmented Autoencoder that combines a U-Net reconstruction component with a patch-level memory bank for nearest-neighbor-based anomaly scoring and outperforming the reconstruction component in AUC-ROC, which is attributable to the robustness of patch-level memory matching for localized structural defects.

Hai Son, D. Ngo · 0 citations
Sep 2026

Domain-Incremental Learning for Multi-Channel Replay Speech Detection

This work frames this as Domain-Incremental Learning over acoustic environments and presents the first continual learning benchmark for multi-channel replay speech detection, evaluating a state-of-the-art beamformer-based detector over all 24 environment orderings of the ReMASC corpus with five seeds.

Michael Neri · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.