# EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

> Research article (2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024) · cited 56× · AI/ML

**Wikidata**: [openalex:W4402727140](https://www.wikidata.org/wiki/openalex:W4402727140)  
**Source**: https://4ort.xyz/entity/emage-towards-unified-holistic-co-speech-gesture-generation-via-expressive-masked-audio-gesture-modeling