Search Results for author:
Found 2 papers, 0 papers with code
Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference
Finally, we employ the diffusion model to train and infer various gestures.
Audio is all in one: speech-driven gesture synthetics using WavLM pre-trained model
Firstly, considering that speech audio not only contains acoustic and semantic features but also conveys personality traits, emotions, and more subtle information related to accompanying gestures, we pioneer the adaptation of WavLM, a large-scale pre-trained model, to extract low-level and high-level audio information.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
