Co-speech gestures are a crucial, non-verbal modality for humans to communicate. Social agents also need this capability to be more human-like and comprehensive. This study aims to model the distribution of gestures conditioned on human speech features. Unlike previous studies that try to find injective functions that map speech to gestures, we propose a novel, conditional GAN-based generative model to not only convert speech into gestures but also to approximate the distribution of gestures conditioned on speech through parameterization. An objective evaluation and user study show that the proposed model outperformed the existing deterministic model, indicating that generative models can approximate real patterns of co-speech gestures better than the existing deterministic model. Our results suggest that it is critical to consider the nature of randomness when modeling co-speech gestures.

Gestures, a form of body language, significantly influence how users perceive humanoid robots. Recent data-driven methods for co-speech gestures have successfully enhanced the naturalness of the generated gestures. Moreover, compared to rule-based systems, these methods are more generalizable for unseen speech input. However, many of these methods cannot directly influence people’s perceptions of robots. The primary challenge lies in the intricacy of constructing a dataset with varied impression labels to develop a conditional generation model. In our prior work ([22]) Controlling the impression of robots via gan-based gesture generation. In:Proceedings of the international conference on intelligent robots and systems. IEEE, pp 9288-9295), we introduced a heuristic approach for automatic labeling, training a deep learning model to control robot impressions. We demonstrated the model’s effectiveness on both a virtual agent and a humanoid robot. In this study, we refined the motion retargeting algorithm for the humanoid robot and conducted a user study using four questions representing different aspects of extroversion. Our results show an improved capability in controlling the perceived degree of extroversion in the humanoid robot compared to previous methods. Furthermore, we discovered that different aspects of extroversion interact uniquely with motion statistics

While it is crucial for human-like avatars to perform co-speech gestures, existing approaches struggle to generate natural and realistic movements. In the present study, a novel transformer-based denoising diffusion model is proposed to generate co-speech gestures. Moreover, we introduce a practical sampling trick for diffusion models to maintain the continuity between the generated motion segments while improving the within-segment motion likelihood and naturalness. Our model can be used for online generation since it generates gestures for a short segment of speech, e.g., 2 s. We evaluate our model on two large-scale speech-gesture datasets with finger movements using objective measurements and a user study, showing that our model outperforms all other baselines. Our user study is based on the Metahuman platform in the Unreal Engine, a popular tool for creating human-like avatars and motions.

Android robots with human-like faces have been developed based on biomimetic principles to reproduce human facial characteristics and expressive behavior. However, the same facial expression may be perceived differently depending on individual perceptual tendencies and conversational context. This study examined whether such subjective evaluations of android facial expressions are reflected in observers’ gaze and facial responses during face-to-face dialogue. Fourteen adults conversed with an android robot and evaluated each facial expression in terms of contextual strangeness and familiarity. Wearable eye tracking was used to measure gaze allocation across facial regions, while participants’ facial movements were extracted from video. Behavioral responses during the 2.5 s following each of the android’s facial-expression events were analyzed. Expressions perceived as strange in the conversational context were associated with reduced mouth-directed gaze and greater activation of several mouth-related blendshapes compared with those perceived as not strange. For unfamiliar expressions, gaze shifted away from the eyes and toward areas outside the face around 1 s after the expression command, whereas familiar expressions showed the opposite pattern. These exploratory findings suggest that subjective perceptions of android facial expressions are reflected in both gaze allocation and facial behavior during interaction.