PRISM proposes a multi-agent system decoupling speech-to-prosody handling, LLM-based response generation, and synthesis, reporting metric improvements in empathy and prosodic fit for spoken dialogue.
Towards multimodal empathetic response generation: A rich text-speech-vision avatar-based benchmark,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue
PRISM proposes a multi-agent system decoupling speech-to-prosody handling, LLM-based response generation, and synthesis, reporting metric improvements in empathy and prosodic fit for spoken dialogue.