Pretrained audio-visual speech encoders adapted with LoRA improve multimodal voice activity projection for turn-taking prediction across multiple languages and a robot mediation corpus.
Towards improving turn-taking in social robots using Visual-Only V oice Activity Detection in multimodal dialogue systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders
Pretrained audio-visual speech encoders adapted with LoRA improve multimodal voice activity projection for turn-taking prediction across multiple languages and a robot mediation corpus.