# Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous Sound Detection

arXiv: https://arxiv.org/abs/2607.04526 · HTML: https://mlsanity.com/paper/2607.04526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Conformal Prediction With Conditional Guarantees](https://mlsanity.com/paper/2305.12616/) (2023)
- [Localized Conformal Prediction: A Generalized Inference Framework for Conformal Prediction](https://mlsanity.com/paper/2106.08460/) (2021)
- [Class-Conditional Conformal Prediction with Many Classes](https://mlsanity.com/paper/2306.09335/) (2023)
- [EAT: Self-Supervised Pre-Training with Efficient Audio Transformer](https://mlsanity.com/paper/2401.03497/) (2024)
- [Conformal prediction with local weights: randomization enables local guarantees](https://mlsanity.com/paper/2310.07850/) (2023)
- [Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density](https://mlsanity.com/paper/2108.10860/) (2021)
- [ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions](https://mlsanity.com/paper/2106.02369/) (2021)
- [MIMII DG: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization Task](https://mlsanity.com/paper/2205.13879/) (2022)
- [First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline](https://mlsanity.com/paper/2303.00455/) (2023)
- [Description and Discussion on DCASE 2025 Challenge Task 2: First-shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring](https://mlsanity.com/paper/2506.10097/) (2025)
- [Local Density-Based Anomaly Score Normalization for Domain Generalization](https://mlsanity.com/paper/2509.10951/) (2025)
- [Deep Generic Representations for Domain-Generalized Anomalous Sound Detection](https://mlsanity.com/paper/2409.05035/) (2024)
- [Handling Domain Shifts for Anomalous Sound Detection: A Review of DCASE-Related Work](https://mlsanity.com/paper/2503.10435/) (2025)
- [Between Resolution Collapse and Variance Inflation: Weighted Conformal Anomaly Detection in Low-Data Regimes](https://mlsanity.com/paper/2603.23205/) (2026)
- [Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring](https://mlsanity.com/paper/2604.20122/) (2026)
- [Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation](https://mlsanity.com/paper/2606.04665/) (2026)
- [Description and Discussion on DCASE 2026 Challenge Task 2: Noise-aware Unsupervised Anomalous Sound Detection for Machine Condition Monitoring](https://mlsanity.com/paper/2606.01578/) (2026)
- [AdaProj: Adaptively Scaled Angular Margin Subspace Projections for Anomalous Sound Detection with Auxiliary Classification Tasks](https://mlsanity.com/paper/2403.14179/) (2024)
- [Set Valued Predictions For Robust Domain Generalization](https://mlsanity.com/paper/2507.03146/) (2025)
- [Scoring Backends Matter More Than Pooling: A Systematic Study of Training-Free Anomalous Sound Detection under Domain Shift](https://mlsanity.com/paper/2606.19269/) (2026)

## Abstract (arXiv)

First-shot anomalous sound detection in DCASE Challenge Task 2 must flag anomalies of unseen machine types with a single threshold, without knowing whether a test clip comes from the data-rich source domain (990 normal training clips) or the data-scarce target domain (10). Two organizer-reported problems remain open: source- and target-domain AUC are negatively correlated across systems, and development-set performance does not predict evaluation-set performance. We address both with a training-free post-hoc layer over frozen audio embeddings: (i) per-domain quantile calibration shrunk toward a pooled map by a prior strength m, tracing a source/target balance frontier, and (ii) a label-free cross-validated domain-balance criterion that ranks candidate configurations from training normals only, paired with a coarse development-labeled viability veto. On DCASE 2025, the criterion rank-predicts the official evaluation score across a 45-configuration grid (Spearman rho = +0.91; family-block bootstrap 95% CI [+0.83, +0.95]) while development score is uninformative (+0.06). Criterion-based selection raises the evaluation score from 55.83 to 59.34 (jackknife CI [2.2, 4.8]) and, on an extended grid, to 61.05 -- retrospectively fourth of 35 teams. Replicating on DCASE 2023 and 2024 bounds the claim: development score is uninformative in all three years and degenerate configurations recur (vetoed every time), but under family-clustered uncertainty the criterion's predictive evidence survives only in 2025; in both replication years a fixed full-equalization default matches or beats criterion-based selection. A DCASE 2026 forward test is frozen before the 2026 evaluation ground truth is released; all headline numbers are reproduced by the official evaluator.