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/

Zendy Plus

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

Zendy Tools

Zendy Open

Transfer learning is critical for efficient information transfer acrossmultiple related learning problems. A simple, yet effective transfer learningapproach utilizes deep neural networks trained on a large-scale task forfeature extraction. Such representations are then used to learn relateddownstream tasks. In this paper, we investigate transfer learning capacity ofaudio representations obtained from neural networks trained on a large-scalesound event detection dataset. We build and evaluate these representationsacross a wide range of other audio tasks, via a simple linear classifiertransfer mechanism. We show that such simple linear transfer is alreadypowerful enough to achieve high performance on the downstream tasks. We alsoprovide insights into the attributes of sound event representations that enablesuch efficient information transfer.

Do sound event representations generalize to other audio tasks? A case study in audio transfer learning