Gestures that accompany speech are an essential part of natural and efficient embodied
human communication. The automatic generation of such co‐speech gestures is a long …

Achieving realistic, vivid, and human-like synthesized conversational gestures conditioned
on multi-modal data is still an unsolved problem due to the lack of available datasets …

This paper reports on the second GENEA Challenge to benchmark data-driven automatic co-
speech gesture generation. Participating teams used the same speech and motion dataset …

Speech-driven gesture generation is highly challenging due to the random jitters of human
motion. In addition, there is an inherent asynchronous relationship between human speech …

Recent deep learning-based approaches have shown promising results for synthesizing
plausible 3D human gestures from speech input. However, these approaches typically offer …

This paper reports on the GENEA Challenge 2023, in which participating teams built speech-
driven gesture-generation systems using the same speech and motion dataset, followed by …

Communication using manual (hand) gestures is considered a defining property of social
robots, and their physical embodiment and presence, therefore, we see a need for a …

Current co-speech gestures synthesis methods struggle with generating diverse motions
and typically collapse to single or few frequent motion sequences, which are trained on …

This paper describes the GestureMaster entry to the GENEA (Generation and Evaluation of
Non-verbal Behaviour for Embodied Agents) Challenge 2022. Given speech audio and text …

With read-aloud speech synthesis achieving high naturalness scores, there is a growing
research interest in synthesising spontaneous speech. However, human spontaneous face …