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

Most audio tagging models are trained with one-hot labels as supervisedinformation. However, one-hot labels treat all sound events equally, ignoringthe semantic hierarchy and proximity relationships between sound events. Incontrast, the event descriptions contains richer information, describing thedistance between different sound events with semantic proximity. In this paper,we explore the impact of training audio tagging models with auxiliary textdescriptions of sound events. By aligning the audio features with the textfeatures of corresponding labels, we inject the hierarchy and proximityinformation of sound events into audio encoders, improving the performancewhile making the prediction more consistent with human perception. We refer tothis approach as Semantic Proximity Alignment (SPA). We use Ontology-aware meanAverage Precision (OmAP) as the main evaluation metric for the models. OmAPreweights the false positives based on Audioset ontology distance and is moreconsistent with human perception compared to mAP. Experimental results showthat the audio tagging models trained with SPA achieve higher OmAP compared tomodels trained with one-hot labels solely (+1.8 OmAP). Human evaluations alsodemonstrate that the predictions of SPA models are more consistent with humanperception.

Semantic Proximity Alignment: Towards Human Perception-consistent Audio Tagging by Aligning with Label Text Description