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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Speech emotion recognition (SER) has been a popular research topic inhuman-computer interaction (HCI). As edge devices are rapidly springing up,applying SER to edge devices is promising for a huge number of HCIapplications. Although deep learning has been investigated to improve theperformance of SER by training complex models, the memory space andcomputational capability of edge devices represents a constraint for embeddingdeep learning models. We propose a neural structured learning (NSL) frameworkthrough building synthesized graphs. An SER model is trained on a sourcedataset and used to build graphs on a target dataset. A relatively lightweightmodel is then trained with the speech samples and graphs together as the input.Our experiments demonstrate that training a lightweight SER model on the targetdataset with speech samples and graphs can not only produce small SER models,but also enhance the model performance compared to models with speech samplesonly and those using classic transfer learning strategies.

Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning