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

WHO's report on environmental noise estimates that 22 M people suffer fromchronic annoyance related to noise caused by audio events (AEs) from varioussources. Annoyance may lead to health issues and adverse effects on metabolicand cognitive systems. In cities, monitoring noise levels does not provideinsights into noticeable AEs, let alone their relations to annoyance. To createannoyance-related monitoring, this paper proposes a graph-based model toidentify AEs in a soundscape, and explore relations between diverse AEs andhuman-perceived annoyance rating (AR). Specifically, this paper proposes alightweight multi-level graph learning (MLGL) based on local and globalsemantic graphs to simultaneously perform audio event classification (AEC) andhuman annoyance rating prediction (ARP). Experiments show that: 1) MLGL with4.1 M parameters improves AEC and ARP results by using semantic nodeinformation in local and global context aware graphs; 2) MLGL capturesrelations between coarse and fine-grained AEs and AR well; 3) Statisticalanalysis of MLGL results shows that some AEs from different sourcessignificantly correlate with AR, which is consistent with previous research onhuman perception of these sound sources.

Multi-level graph learning for audio event classification and human-perceived annoyance rating prediction