LLM-based beam search disambiguation improves dictionary sign spotting WER from 47.2% to 44.4% on an internal BSL dataset.
Berndt and James Clifford
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sign Spotting Disambiguation using Large Language Models
LLM-based beam search disambiguation improves dictionary sign spotting WER from 47.2% to 44.4% on an internal BSL dataset.