Preserving Speaker Information in Direct Speech-to-Speech Translation with Non-Autoregressive Generation and Pretraining

Documenti analoghi

• REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion
  di: Biyani, Ishan D., et al.
  Pubblicazione: (2025)
• Low-latency Speech Enhancement via Speech Token Generation
  di: Xue, Huaying, et al.
  Pubblicazione: (2023)
• RAVSS: Robust Audio-Visual Speech Separation in Multi-Speaker Scenarios with Missing Visual Cues
  di: Pan, Tianrui, et al.
  Pubblicazione: (2024)
• ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation
  di: Shi, Jiatong, et al.
  Pubblicazione: (2025)
• Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge Distillation
  di: Cui, Yang, et al.
  Pubblicazione: (2025)