Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM

Documenti analoghi

• Adapting WavLM for Speech Emotion Recognition
  di: Diatlova, Daria, et al.
  Pubblicazione: (2024)
• Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection
  di: Stourbe, Theophile, et al.
  Pubblicazione: (2024)
• Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation
  di: Ruggiero, Giuseppe, et al.
  Pubblicazione: (2025)
• Frame-Aligned Fusion of Canary and WavLM for Non-Intrusive Intelligibility Prediction of Hearing-Aid-Processed Speech
  di: Nakazawa, Kazushi
  Pubblicazione: (2026)
• SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech
  di: Lin, Jingru, et al.
  Pubblicazione: (2024)