English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

First-shot (FS) unsupervised anomalous sound detection (ASD) is a brand-newtask introduced in DCASE 2023 Challenge Task 2, where the anomalous sounds forthe target machine types are unseen in training. Existing methods often rely onthe availability of normal and abnormal sound data from the target machines.However, due to the lack of anomalous sound data for the target machine types,it becomes challenging when adapting the existing ASD methods to the first-shottask. In this paper, we propose a new framework for the first-shot unsupervisedASD, where metadata-assisted audio generation is used to estimate unknownanomalies, by utilising the available machine information (i.e., metadata andsound data) to fine-tune a text-to-audio generation model for generating theanomalous sounds that contain unique acoustic characteristics accounting foreach different machine types. We then use the method of Time-Weighted Frequencydomain audio Representation with Gaussian Mixture Model (TWFR-GMM) as thebackbone to achieve the first-shot unsupervised ASD. Our proposed FS-TWFR-GMMmethod achieves competitive performance amongst top systems in DCASE 2023Challenge Task 2, while requiring only 1% model parameters for detection, asvalidated in our experiments.

First-Shot Unsupervised Anomalous Sound Detection With Unknown Anomalies Estimated by Metadata-Assisted Audio Generation