No Gestures Left Behind: Learning Relationships between Spoken Language and Freeform Gestures
We study relationships between spoken language and co-speech gestures in context of two key challenges. First, distributions of text and gestures are inherently skewed making it important to model the long tail. Second, gesture predictions are made at a subword level, making it important to learn relationships between language and audio. We introduce Adversarial Importance Sampled Learning, which combines adversarial learning with importance sampling to strike a balance between precision and coverage. We substantiate the effectiveness of our approach through large-scale quantitative and user studies, which show that our proposed methodology significantly outperforms previous stateof-the-art approaches for gesture generation.
PDF Abstract