A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition.

Tyler Benster Guy H. Wilson Reshef Elisha Francis R. Willett Shaul Druckmann

Published in: CoRR (2024)

Keyphrases

cross modal
visual recognition
multi modal
object recognition
multimedia retrieval
image retrieval
multimedia databases
visual similarity
feature extraction
text retrieval
activity recognition
visual data
action recognition
semantic concepts
eye movements
image classification
image sequences