Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering

Documenti analoghi

• Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition
  di: Zhang, Yiru, et al.
  Pubblicazione: (2025)
• AudioEval: Automatic Dual-Perspective and Multi-Dimensional Evaluation of Text-to-Audio-Generation
  di: Wang, Hui, et al.
  Pubblicazione: (2025)
• MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation
  di: Liu, Cheng, et al.
  Pubblicazione: (2025)
• WildElder: A Chinese Elderly Speech Dataset from the Wild with Fine-Grained Manual Annotations
  di: Wang, Hui, et al.
  Pubblicazione: (2025)
• Iterative Prototype Refinement for Ambiguous Speech Emotion Recognition
  di: Sun, Haoqin, et al.
  Pubblicazione: (2024)