Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis

Documenti analoghi

• Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis
  di: Lemerle, Théodor, et al.
  Pubblicazione: (2024)
• Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction
  di: Guichoux, Téo, et al.
  Pubblicazione: (2025)
• Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters
  di: Abrassart, Mathilde, et al.
  Pubblicazione: (2025)
• 2D or not 2D: How Does the Dimensionality of Gesture Representation Affect 3D Co-Speech Gesture Generation?
  di: Guichoux, Téo, et al.
  Pubblicazione: (2024)
• FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer
  di: Wang, Haoxu, et al.
  Pubblicazione: (2025)