@inproceedings{ec718ed0dd8740628eb2e6bffc127fd7,
title = "Real-time Gesture Animation Generation from Speech for Virtual Human Interaction",
abstract = "We propose a real-time system for synthesizing gestures directly from speech. Our data-driven approach is based on Generative Adversarial Neural Networks to model the speech-gesture relationship. We utilize the large amount of speaker video data available online to train our 3D gesture model. Our model generates speaker-specific gestures by taking consecutive audio input chunks of two seconds in length. We animate the predicted gestures on a virtual avatar. We achieve a delay below three seconds between the time of audio input and gesture animation.",
keywords = "Animation, Gestures, NUI",
author = "Manuel Rebol and Christian G{\"u}tl and Krzysztof Pietroszek",
note = "Funding Information: This work was supported in part by the Marshall Plan Foundation and the National Science Foundation. Publisher Copyright: {\textcopyright} 2021 Owner/Author.; 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths : CHI 2021 ; Conference date: 08-05-2021 Through 13-05-2021",
year = "2021",
month = may,
day = "8",
doi = "10.1145/3411763.3451554",
language = "English",
series = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association of Computing Machinery",
pages = "327--344",
booktitle = "Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, CHI EA 2021",
address = "United States",
}