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

Embodied agents, in the form of virtual agents or social robots, are rapidlybecoming more widespread. In human-human interactions, humans use nonverbalbehaviours to convey their attitudes, feelings, and intentions. Therefore, thiscapability is also required for embodied agents in order to enhance the qualityand effectiveness of their interactions with humans. In this paper, we proposea novel framework that can generate sequences of joint angles from the speechtext and speech audio utterances. Based on a conditional Generative AdversarialNetwork (GAN), our proposed neural network model learns the relationshipsbetween the co-speech gestures and both semantic and acoustic features from thespeech input. In order to train our neural network model, we employ a publicdataset containing co-speech gestures with corresponding speech audioutterances, which were captured from a single male native English speaker. Theresults from both objective and subjective evaluations demonstrate the efficacyof our gesture-generation framework for Robots and Embodied Agents.

Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents