Self-Supervised Speech Representations are More Phonetic than Semantic

Documenti analoghi

• What Do Self-Supervised Speech Models Know About Words?
  di: Pasad, Ankita, et al.
  Pubblicazione: (2023)
• Discrete Speech Unit Extraction via Independent Component Analysis
  di: Nakamura, Tomohiko, et al.
  Pubblicazione: (2025)
• What do Speech Foundation Models Learn? Analysis and Applications
  di: Pasad, Ankita
  Pubblicazione: (2025)
• On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
  di: Tian, Jinchuan, et al.
  Pubblicazione: (2024)
• Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment
  di: Choi, Kwanghee, et al.
  Pubblicazione: (2025)