Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners

Documenti analoghi

• Reading to Listen at the Cocktail Party: Multi-Modal Speech Separation
  di: Rahimi, Akam, et al.
  Pubblicazione: (2025)
• Recent Advances in Discrete Speech Tokens: A Review
  di: Guo, Yiwei, et al.
  Pubblicazione: (2025)
• Bridging the Gap: Integrating Pre-trained Speech Enhancement and Recognition Models for Robust Speech Recognition
  di: Wang, Kuan-Chen, et al.
  Pubblicazione: (2024)
• Next Tokens Denoising for Speech Synthesis
  di: Liu, Yanqing, et al.
  Pubblicazione: (2025)
• Confidence-Based Self-Training for EMG-to-Speech: Leveraging Synthetic EMG for Robust Modeling
  di: Chen, Xiaodan, et al.
  Pubblicazione: (2025)