Next Tokens Denoising for Speech Synthesis

Documenti analoghi

• Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners
  di: Yuan, Ze, et al.
  Pubblicazione: (2024)
• Autoregressive Speech Synthesis without Vector Quantization
  di: Meng, Lingwei, et al.
  Pubblicazione: (2024)
• FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
  di: Wang, Hui, et al.
  Pubblicazione: (2025)
• VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment
  di: Han, Bing, et al.
  Pubblicazione: (2024)
• VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
  di: Chen, Sanyuan, et al.
  Pubblicazione: (2024)