Reproduce “Rhythmic-Semantic Co-Speech Gestures for Emotional Dialogue in Robots” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Christian Arzate Cruz, Edwin C. Montiel-Vázquez, Stefanos Gkikas, Miguel Mejia Tobar, Randy Gomez
G-BERT combines iconic gestures that convey meaning with rhythmic beats for social robots. Given text and intended emotion, it predicts iconic placement and intensity, then fills remaining spans with beats. In an online video study, viewers rated speech–gesture correlation higher than LLM and random baselines, with only a positive trend over ground-truth labels. The study evaluated Haru only.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.