The authors combine an LLM, motion matching, and a pose-to-video model to generate ASL videos with non-manual markers, reporting a BLEU-4 of 0.276 for text-to-gloss and a user study where DHH participants rated generated videos lower than human signing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards AI-driven Sign Language Generation with Non-manual Markers
The authors combine an LLM, motion matching, and a pose-to-video model to generate ASL videos with non-manual markers, reporting a BLEU-4 of 0.276 for text-to-gloss and a user study where DHH participants rated generated videos lower than human signing.