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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper proposes an approach for anomalous sound detection thatincorporates outlier exposure and inlier modeling within a unified framework bymultitask learning. While outlier exposure-based methods can extract featuresefficiently, it is not robust. Inlier modeling is good at generating robustfeatures, but the features are not very effective. Recently, serial approachesare proposed to combine these two methods, but it still requires a separatetraining step for normal data modeling. To overcome these limitations, we usemultitask learning to train a conformer-based encoder for outlier-aware inliermodeling. Moreover, our approach provides multi-scale scores for detectinganomalies. Experimental results on the MIMII and DCASE 2020 task 2 datasetsshow that our approach outperforms state-of-the-art single-model systems andachieves comparable results with top-ranked multi-system ensembles.

Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning