Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation
- Publisher:
- Association for Computing Machinery (ACM)
- Publication Type:
- Conference Proceeding
- Citation:
- ACM International Conference Proceeding Series, 2022, pp. 748-752
- Issue Date:
- 2022-11-07
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation.pdf | Published version | 768.45 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
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.
Please use this identifier to cite or link to this item: