Pith. sign in

REVIEW

Transformer-based Autoencoder with ID Constraint for Unsupervised Anomalous Sound Detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.08950 v1 pith:MG2OTH5P submitted 2023-10-13 cs.SD eess.AS

Transformer-based Autoencoder with ID Constraint for Unsupervised Anomalous Sound Detection

classification cs.SD eess.AS
keywords anomaloussoundautoencodermethodsanomalynormalsoundstransformer-based
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods. However, the AE-based methods could be limited as the feature learned from normal sounds can also fit with anomalous sounds, reducing the ability of the model in detecting anomalies from sound. The self-supervised methods are not always stable and perform differently, even for machines of the same type. In addition, the anomalous sound may be short-lived, making it even harder to distinguish from normal sound. This paper proposes an ID constrained Transformer-based autoencoder (IDC-TransAE) architecture with weighted anomaly score computation for unsupervised ASD. Machine ID is employed to constrain the latent space of the Transformer-based autoencoder (TransAE) by introducing a simple ID classifier to learn the difference in the distribution for the same machine type and enhance the ability of the model in distinguishing anomalous sound. Moreover, weighted anomaly score computation is introduced to highlight the anomaly scores of anomalous events that only appear for a short time. Experiments performed on DCASE 2020 Challenge Task2 development dataset demonstrate the effectiveness and superiority of our proposed method.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.