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

The capability for environmental sound recognition (ESR) can determine thefitness of individuals in a way to avoid dangers or pursue opportunities whencritical sound events occur. It still remains mysterious about the fundamentalprinciples of biological systems that result in such a remarkable ability.Additionally, the practical importance of ESR has attracted an increasingamount of research attention, but the chaotic and non-stationary difficultiescontinue to make it a challenging task. In this study, we propose a spike-basedframework from a more brain-like perspective for the ESR task. Our framework isa unifying system with a consistent integration of three major functional partswhich are sparse encoding, efficient learning and robust readout. We firstintroduce a simple sparse encoding where key-points are used for featurerepresentation, and demonstrate its generalization to both spike and non-spikebased systems. Then, we evaluate the learning properties of different learningrules in details with our contributions being added for improvements. Ourresults highlight the advantages of the multi-spike learning, providing aselection reference for various spike-based developments. Finally, we combinethe multi-spike readout with the other parts to form a system for ESR.Experimental results show that our framework performs the best as compared toother baseline approaches. In addition, we show that our spike-based frameworkhas several advantageous characteristics including early decision making, smalldataset acquiring and ongoing dynamic processing. Our framework is the firstattempt to apply the multi-spike characteristic of nervous neurons to ESR. Theoutstanding performance of our approach would potentially contribute to drawmore research efforts to push the boundaries of spike-based paradigm to a newhorizon.

Robust Environmental Sound Recognition with Sparse Key-point Encoding and Efficient Multi-spike Learning