Source Tracing of Synthetic Speech Systems Through Paralinguistic Pre-Trained Representations

Ähnliche Einträge

• Rethinking Cross-Corpus Speech Emotion Recognition Benchmarking: Are Paralinguistic Pre-Trained Representations Sufficient?
  von: Phukan, Orchid Chetia, et al.
  Veröffentlicht: (2025)
• HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition
  von: Phukan, Orchid Chetia, et al.
  Veröffentlicht: (2025)
• Investigating the Reasonable Effectiveness of Speaker Pre-Trained Models and their Synergistic Power for SingMOS Prediction
  von: Phukan, Orchid Chetia, et al.
  Veröffentlicht: (2025)
• Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models
  von: Phukan, Orchid Chetia, et al.
  Veröffentlicht: (2025)
• Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
  von: Phukan, Orchid Chetia, et al.
  Veröffentlicht: (2024)