Investigating the Reasonable Effectiveness of Speaker Pre-Trained Models and their Synergistic Power for SingMOS Prediction

Documents similaires

• HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition
  par: Phukan, Orchid Chetia, et autres
  Publié: (2025)
• Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models
  par: Phukan, Orchid Chetia, et autres
  Publié: (2025)
• Source Tracing of Synthetic Speech Systems Through Paralinguistic Pre-Trained Representations
  par: Girish, et autres
  Publié: (2025)
• Rethinking Cross-Corpus Speech Emotion Recognition Benchmarking: Are Paralinguistic Pre-Trained Representations Sufficient?
  par: Phukan, Orchid Chetia, et autres
  Publié: (2025)
• Beyond Speech and More: Investigating the Emergent Ability of Speech Foundation Models for Classifying Physiological Time-Series Signals
  par: Phukan, Orchid Chetia, et autres
  Publié: (2024)