A conditional GAN framework generates co-speech gesture sequences of joint angles from speech text and audio for embodied agents, trained on a single-speaker public dataset and assessed via objective and subjective evaluations.
Style transfer for co-speech gesture animation: A multi-speaker conditional-mixture approach,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents
A conditional GAN framework generates co-speech gesture sequences of joint angles from speech text and audio for embodied agents, trained on a single-speaker public dataset and assessed via objective and subjective evaluations.