LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling

Documenti analoghi

• CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS
  di: Chen, Junyang, et al.
  Pubblicazione: (2026)
• Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
  di: Jiang, Ziyue, et al.
  Pubblicazione: (2023)
• ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis
  di: Li, Haitao, et al.
  Pubblicazione: (2026)
• CLAR: CIF-Localized Alignment for Retrieval-Augmented Speech LLM-Based Contextual ASR
  di: Huang, Shangkun, et al.
  Pubblicazione: (2026)
• MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
  di: Jiang, Ziyue, et al.
  Pubblicazione: (2025)