A hierarchical cross-modal fusion architecture with LoRA adapters predicts human perception of AI-dubbed clips at PCC > 0.75 after training on 12k Hindi-English examples and human MOS fine-tuning.
Dub- wise: Video-guided speech duration control in multi- modal llm-based text-to-speech for dubbing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Can Hierarchical Cross-Modal Fusion Predict Human Perception of AI Dubbed Content?
A hierarchical cross-modal fusion architecture with LoRA adapters predicts human perception of AI-dubbed clips at PCC > 0.75 after training on 12k Hindi-English examples and human MOS fine-tuning.