Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations

Documenti analoghi

• Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models
  di: Gubian, Michele, et al.
  Pubblicazione: (2025)
• A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech
  di: Liu, Oli Danyi, et al.
  Pubblicazione: (2024)
• The role of audio-visual integration in the time course of phonetic encoding in self-supervised speech models
  di: Wang, Yi, et al.
  Pubblicazione: (2025)
• A framework for analyzing concept representations in neural models
  di: Naowarat, Burin, et al.
  Pubblicazione: (2026)
• Sustainable self-supervised learning for speech representations
  di: Lugo, Luis, et al.
  Pubblicazione: (2024)