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

This report proposes a frequency dynamic convolution (FDY) with a largekernel attention (LKA)-convolutional recurrent neural network (CRNN) with apre-trained bidirectional encoder representation from audio transformers(BEATs) embedding-based sound event detection (SED) model that employs amean-teacher and pseudo-label approach to address the challenge of limitedlabeled data for DCASE 2023 Task 4. The proposed FDY with LKA integrates theFDY and LKA module to effectively capture time-frequency patterns, long-termdependencies, and high-level semantic information in audio signals. Theproposed FDY with LKA-CRNN with a BEATs embedding network is initially trainedon the entire DCASE 2023 Task 4 dataset using the mean-teacher approach,generating pseudo-labels for weakly labeled, unlabeled, and the AudioSet.Subsequently, the proposed SED model is retrained using the same pseudo-labelapproach. A subset of these models is selected for submission, demonstratingsuperior F1-scores and polyphonic SED score performance on the DCASE 2023Challenge Task 4 validation dataset.

Semi-supervsied Learning-based Sound Event Detection using Freuqency Dynamic Convolution with Large Kernel Attention for DCASE Challenge 2023 Task 4