Magnitude-Phase Dual-Path Speech Enhancement Network based on Self-Supervised Embedding and Perceptual Contrast Stretch Boosting

Documenti analoghi

• BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embedding
  di: Mattursun, Alimjan, et al.
  Pubblicazione: (2024)
• Semantic-Emotional Resonance Embedding: A Semi-Supervised Paradigm for Cross-Lingual Speech Emotion Recognition
  di: Zhao, Ya, et al.
  Pubblicazione: (2026)
• Exploiting Consistency-Preserving Loss and Perceptual Contrast Stretching to Boost SSL-based Speech Enhancement
  di: Khan, Muhammad Salman, et al.
  Pubblicazione: (2024)
• PCQ: Emotion Recognition in Speech via Progressive Channel Querying
  di: Wang, Xincheng, et al.
  Pubblicazione: (2024)
• AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis
  di: Cao, Yubing, et al.
  Pubblicazione: (2025)