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

Audio event localization and detection (SELD) have been commonly tackledusing multitask models. Such a model usually consists of a multi-label eventclassification branch with sigmoid cross-entropy loss for event activitydetection and a regression branch with mean squared error loss fordirection-of-arrival estimation. In this work, we propose a multitaskregression model, in which both (multi-label) event detection and localizationare formulated as regression problems and use the mean squared error losshomogeneously for model training. We show that the common combination ofheterogeneous loss functions causes the network to underfit the data whereasthe homogeneous mean squared error loss leads to better convergence andperformance. Experiments on the development and validation sets of the DCASE2020 SELD task demonstrate that the proposed system also outperforms the DCASE2020 SELD baseline across all the detection and localization metrics, reducingthe overall SELD error (the combined metric) by approximately 10% absolute.

On Multitask Loss Function for Audio Event Detection and Localization