A three-agent script-writer, synthesizer, and critic pipeline generates a bilingual multi-party speech dataset whose quality matches manually assembled datasets in TTS training benchmarks.
Naturalspeech 2: Latent diffusion models are natural and zero- shot speech and singing synthesizers,
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
-
DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue
A three-agent script-writer, synthesizer, and critic pipeline generates a bilingual multi-party speech dataset whose quality matches manually assembled datasets in TTS training benchmarks.