Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder

Documenti analoghi

• Disentangling Pitch and Creak for Speaker Identity Preservation in Speech Synthesis
  di: Rautenberg, Frederik, et al.
  Pubblicazione: (2026)
• Speech Synthesis along Perceptual Voice Quality Dimensions
  di: Rautenberg, Frederik, et al.
  Pubblicazione: (2025)
• Microphone Array Signal Processing and Deep Learning for Speech Enhancement
  di: Haeb-Umbach, Reinhold, et al.
  Pubblicazione: (2025)
• Towards Frame-level Quality Predictions of Synthetic Speech
  di: Kuhlmann, Michael, et al.
  Pubblicazione: (2025)
• Speech Quality Embeddings for Improved Detection and Classification of Degradations in Speech Signals
  di: Kuhlmann, Michael, et al.
  Pubblicazione: (2026)