DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech

Documents similaires

• Learning Physiology-Informed Vocal Spectrotemporal Representations for Speech Emotion Recognition
  par: Zhang, Xu, et autres
  Publié: (2026)
• AmbER$^2$: Dual Ambiguity-Aware Emotion Recognition Applied to Speech and Text
  par: Wu, Jingyao, et autres
  Publié: (2026)
• Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis
  par: Inoue, Sho, et autres
  Publié: (2024)
• DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching
  par: Xie, Hanke, et autres
  Publié: (2025)
• Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models
  par: Jing, Xin, et autres
  Publié: (2024)