EASL: Multi-Emotion Guided Semantic Disentanglement for Expressive Sign Language Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908677794955264 |
|---|---|
| author | Zhao, Yanchao Zhu, Jihao Liu, Yu Chen, Weizhuo Yang, Yuling Peng, Kun |
| author_facet | Zhao, Yanchao Zhu, Jihao Liu, Yu Chen, Weizhuo Yang, Yuling Peng, Kun |
| contents | Large language models have revolutionized sign language generation by automatically transforming text into high-quality sign language videos, providing accessible communication for the Deaf community. However, existing LLM-based approaches prioritize semantic accuracy while overlooking emotional expressions, resulting in outputs that lack naturalness and expressiveness. We propose EASL (Emotion-Aware Sign Language), a multi-emotion-guided generation architecture for fine-grained emotional integration. We introduce emotion-semantic disentanglement modules with progressive training to separately extract semantic and affective features. During pose decoding, the emotional representations guide semantic interaction to generate sign poses with 7-class emotion confidence scores, enabling emotional expression recognition. Experimental results demonstrate that EASL achieves pose accuracy superior to all compared baselines by integrating multi-emotion information and effectively adapts to diffusion models to generate expressive sign language videos. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EASL: Multi-Emotion Guided Semantic Disentanglement for Expressive Sign Language Generation Zhao, Yanchao Zhu, Jihao Liu, Yu Chen, Weizhuo Yang, Yuling Peng, Kun Computer Vision and Pattern Recognition Large language models have revolutionized sign language generation by automatically transforming text into high-quality sign language videos, providing accessible communication for the Deaf community. However, existing LLM-based approaches prioritize semantic accuracy while overlooking emotional expressions, resulting in outputs that lack naturalness and expressiveness. We propose EASL (Emotion-Aware Sign Language), a multi-emotion-guided generation architecture for fine-grained emotional integration. We introduce emotion-semantic disentanglement modules with progressive training to separately extract semantic and affective features. During pose decoding, the emotional representations guide semantic interaction to generate sign poses with 7-class emotion confidence scores, enabling emotional expression recognition. Experimental results demonstrate that EASL achieves pose accuracy superior to all compared baselines by integrating multi-emotion information and effectively adapts to diffusion models to generate expressive sign language videos. |
| title | EASL: Multi-Emotion Guided Semantic Disentanglement for Expressive Sign Language Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.22135 |