Co-speech gestures increase engagement and improve speech understanding. Most data-driven robot systems generate rhythmic beat-like motion, yet few integrate semantic emphasis. To address this, we propose a lightweight transformer that derives iconic gesture placement and intensity from text and emotion alone, requiring no audio input at inference time. The model outperforms GPT-4o in both semantic gesture placement classification and intensity regression on the BEAT2 dataset, while remaining computationally compact and suitable for real-time deployment on embodied agents.
@article{arxiv.2604.11417,
title = {Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech},
author = {Edwin C. Montiel-Vazquez and Christian Arzate Cruz and Stefanos Gkikas and Thomas Kassiotis and Giorgos Giannakakis and Randy Gomez},
journal= {arXiv preprint arXiv:2604.11417},
year = {2026}
}