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

Audio tagging aims to assign predefined tags to audio clips to indicate theclass information of audio events. Sequential audio tagging (SAT) meansdetecting both the class information of audio events, and the order in whichthey occur within the audio clip. Most existing methods for SAT are based onconnectionist temporal classification (CTC). However, CTC cannot effectivelycapture connections between events due to the conditional independenceassumption between outputs at different times. The contextual Transformer(cTransformer) addresses this issue by exploiting contextual information inSAT. Nevertheless, cTransformer is also limited in exploiting contextualinformation as it only uses forward information in inference. This paperproposes a gated contextual Transformer (GCT) with forward-backward inference(FBI). In addition, a gated contextual multi-layer perceptron (GCMLP) block isproposed in GCT to improve the performance of cTransformer structurally.Experiments on two real-life audio datasets show that the proposed GCT withGCMLP and FBI performs better than the CTC-based methods and cTransformer. Topromote research on SAT, the manually annotated sequential labels for the twodatasets are released.

GCT: Gated Contextual Transformer for Sequential Audio Tagging