TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers

Ähnliche Einträge

• ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering
  von: Song, Yakun, et al.
  Veröffentlicht: (2024)
• Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
  von: Wang, Tianrui, et al.
  Veröffentlicht: (2025)
• Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
  von: Yang, Yifan, et al.
  Veröffentlicht: (2025)
• VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
  von: Chen, Sanyuan, et al.
  Veröffentlicht: (2024)
• CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
  von: Kim, Jaehyeon, et al.
  Veröffentlicht: (2024)