Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation

Khaled Saleh

Track: Challenge paper

Team Name: DSI

Abstract: This paper describes the co-speech gesture generation system developed by DSI team for the GENEA challenge 2022. The proposed framework features a unique hybrid encoder-decoder architecture based on transformer networks and recurrent neural networks. The proposed framework has been trained using only the official training data split of the challenge and its performance has been evaluated on the testing split. The framework has achieved promising results on both the subjective (specially the human-likeness) and objective evaluation metrics.