What is it about?
We present a machine-learning model that can generate 3D gesture movements based on speech. It is using a chain of several neural networks and performs better than the baseline.
Featured Image
Photo by Vidar Nordli-Mathisen on Unsplash
Why is it important?
Human communication is to a large extend non-verbal. While talking, people spontaneously gesticulate, which plays a key role in conveying information. If we want interaction with social agents (such as robots or virtual avatars) to be natural and smooth we need to enable them to gesticulate as well.
Read the Original
This page is a summary of: Analyzing Input and Output Representations for Speech-Driven Gesture Generation, July 2019, ACM (Association for Computing Machinery),
DOI: 10.1145/3308532.3329472.
You can read the full text:
Contributors
The following have contributed to this page