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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recently, convolutional neural networks (CNNs) have been widely used in soundevent detection (SED). However, traditional convolution is deficient inlearning time-frequency domain representation of different sound events. Toaddress this issue, we propose multi-dimensional frequency dynamic convolution(MFDConv), a new design that endows convolutional kernels withfrequency-adaptive dynamic properties along multiple dimensions. MFDConvutilizes a novel multi-dimensional attention mechanism with a parallel strategyto learn complementary frequency-adaptive attentions, which substantiallystrengthen the feature extraction ability of convolutional kernels. Moreover,in order to promote the performance of mean teacher, we propose the confidentmean teacher to increase the accuracy of pseudo-labels from the teacher andtrain the student with high confidence labels. Experimental results show thatthe proposed methods achieve 0.470 and 0.692 of PSDS1 and PSDS2 on the DESEDreal validation dataset.

Multi-dimensional frequency dynamic convolution with confident mean teacher for sound event detection