SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer

Documenti analoghi

• Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models
  di: Phukan, Orchid Chetia, et al.
  Pubblicazione: (2025)
• Investigating the Reasonable Effectiveness of Speaker Pre-Trained Models and their Synergistic Power for SingMOS Prediction
  di: Phukan, Orchid Chetia, et al.
  Pubblicazione: (2025)
• HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition
  di: Phukan, Orchid Chetia, et al.
  Pubblicazione: (2025)
• PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition
  di: Phukan, Orchid Chetia, et al.
  Pubblicazione: (2025)
• Investigating Polyglot Speech Foundation Models for Learning Collective Emotion from Crowds
  di: Phukan, Orchid Chetia, et al.
  Pubblicazione: (2025)