M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesis

Documenti analoghi

• DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech
  di: Qi, Xin, et al.
  Pubblicazione: (2024)
• Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation
  di: Guo, Hongming, et al.
  Pubblicazione: (2024)
• RPRA-ADD: Forgery Trace Enhancement-Driven Audio Deepfake Detection
  di: Fu, Ruibo, et al.
  Pubblicazione: (2025)
• ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation
  di: Fu, Ruibo, et al.
  Pubblicazione: (2024)
• GACA-DiT: Diffusion-based Dance-to-Music Generation with Genre-Adaptive Rhythm and Context-Aware Alignment
  di: Wang, Jinting, et al.
  Pubblicazione: (2025)