Retaining Mixture Representations for Domain Generalized Anomalous Sound Detection

TL;DR

This paper introduces a retain-not-denoise strategy for SSL-based anomalous sound detection, enhancing robustness to distribution shifts by preserving mixture information rather than suppressing noise.

Contribution

It proposes a novel mixture alignment loss that improves SSL backbone performance in noisy, mismatched sound environments for ASD.

Findings

Improved robustness under distribution shifts.

Narrowed gap to oracle mixture representations.

Enhanced performance on various noise subsets.

Abstract

Anomalous sound detection (ASD) in the wild requires robustness to distribution shifts such as unseen low-SNR input mixtures of machine and noise types. State-of-the-art systems extract embeddings from an adapted audio encoder and detect anomalies via nearest-neighbor search, but fine tuning on noisy machine sounds often acts like a denoising objective, suppressing noise and reducing generalization under mismatched mixtures or inconsistent labeling. Training-free systems with frozen self-supervised learning (SSL) encoders avoid this issue and show strong first-shot generalization, yet their performance drops when mixture embeddings deviate from clean-source embeddings. We propose to improve SSL backbones with a retain-not-denoise strategy that better preserves information from mixed sound sources. The approach combines a multi-label audio tagging loss with a mixture alignment loss that aligns student mixture embeddings to convex teacher embeddings of clean and noise inputs. Controlled experiments on stationary, non-stationary, and mismatched noise subsets demonstrate improved robustness under distribution shifts, narrowing the gap toward oracle mixture representations.