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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Large-scale sound recognition data sets typically consist of acousticrecordings obtained from multimedia libraries. As a consequence, modalitiesother than audio can often be exploited to improve the outputs of modelsdesigned for associated tasks. Frequently, however, not all contents areavailable for all samples of such a collection: For example, the originalmaterial may have been removed from the source platform at some point, andtherefore, non-auditory features can no longer be acquired.  We demonstrate that a multi-encoder framework can be employed to deal withthis issue by applying this method to attention-based deep learning systems,which are currently part of the state of the art in the domain of soundrecognition. More specifically, we show that the proposed model extension cansuccessfully be utilized to incorporate partially available visual informationinto the operational procedures of such networks, which normally only useauditory features during training and inference. Experimentally, we verify thatthe considered approach leads to improved predictions in a number of evaluationscenarios pertaining to audio tagging and sound event detection. Additionally,we scrutinize some properties and limitations of the presented technique.

Multi-encoder attention-based architectures for sound recognition with partial visual assistance