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

Speech Emotion Recognition (SER) refers to the recognition of human emotionsfrom natural speech. If done accurately, it can offer a number of benefits inbuilding human-centered context-aware intelligent systems. Existing SERapproaches are largely centralized, without considering users' privacy.Federated Learning (FL) is a distributed machine learning paradigm dealing withdecentralization of privacy-sensitive personal data. In this paper, we presenta privacy-preserving and data-efficient SER approach by utilizing the conceptof FL. To the best of our knowledge, this is the first federated SER approach,which utilizes self-training learning in conjunction with federated learning toexploit both labeled and unlabeled on-device data. Our experimental evaluationson the IEMOCAP dataset shows that our federated approach can learngeneralizable SER models even under low availability of data labels and highlynon-i.i.d. distributions. We show that our approach with as few as 10% labeleddata, on average, can improve the recognition rate by 8.67% compared to thefully-supervised federated counterparts.

Privacy-preserving Speech Emotion Recognition through Semi-Supervised Federated Learning