Adding a pretrained facial-expression encoder to a voice activity projection model yields competitive or slightly better turn-taking prediction on the NoXi French subset, though the improvement is not statistically validated.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Voice Activity Projection Model with Multimodal Encoders
Adding a pretrained facial-expression encoder to a voice activity projection model yields competitive or slightly better turn-taking prediction on the NoXi French subset, though the improvement is not statistically validated.