Description and Discussion on DCASE 2025 Challenge Task 2: First-shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

TL;DR

This paper details the DCASE 2025 Challenge Task 2, focusing on first-shot unsupervised anomalous sound detection for machine monitoring, emphasizing rapid deployment without machine-specific tuning and analyzing diverse approaches from participants.

Contribution

It introduces a new challenge task framework for domain generalization in ASD, with a comprehensive analysis of participant methods and their effectiveness.

Findings

Various approaches like fine-tuning and frozen models are competitive.

Proper cost functions and normalization improve detection.

Unseen machine sounds are effectively evaluated.

Abstract

This paper introduces the task description for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge Task 2, titled "First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring". Building on the DCASE 2024 Challenge Task 2, this task is structured as a first-shot problem within a domain generalization framework. The primary objective of the first-shot approach is to facilitate the rapid deployment of ASD systems for new machine types without requiring machine-specific hyperparameter tunings. For DCASE 2025 Challenge Task 2, sounds from previously unseen machine types have been collected and provided as the evaluation dataset. We received 119 submissions from 35 teams, and an analysis of these submissions has been made in this paper. Analysis showed that various approaches can all be competitive, such as fine-tuning pre-trained models, using frozen pre-trained models, and training small models from scratch, when combined with appropriate cost functions, anomaly score normalization, and use of clean machine and noise sounds.