Using UMAP to Inspect Audio Data for Unsupervised Anomaly Detection under Domain-Shift Conditions
This is an incremental exploratory study for audio anomaly detection researchers, focusing on diagnostic insights rather than new methods or benchmarks.
The paper tackled the problem of unsupervised anomaly detection in audio data under domain-shift conditions by visually inspecting UMAP projections of different audio representations, formulating hypotheses about trade-offs between separability and discriminative support without providing concrete detection results or numbers.
The goal of Unsupervised Anomaly Detection (UAD) is to detect anomalous signals under the condition that only non-anomalous (normal) data is available beforehand. In UAD under Domain-Shift Conditions (UAD-S), data is further exposed to contextual changes that are usually unknown beforehand. Motivated by the difficulties encountered in the UAD-S task presented at the 2021 edition of the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge, we visually inspect Uniform Manifold Approximations and Projections (UMAPs) for log-STFT, log-mel and pretrained Look, Listen and Learn (L3) representations of the DCASE UAD-S dataset. In our exploratory investigation, we look for two qualities, Separability (SEP) and Discriminative Support (DSUP), and formulate several hypotheses that could facilitate diagnosis and developement of further representation and detection approaches. Particularly, we hypothesize that input length and pretraining may regulate a relevant tradeoff between SEP and DSUP. Our code as well as the resulting UMAPs and plots are publicly available.