BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

Documenti analoghi

• Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity
  di: Peurey, Loann, et al.
  Pubblicazione: (2025)
• Context-aware child-directed speech detection from long-form recordings
  di: Charlot, Théo, et al.
  Pubblicazione: (2026)
• Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier
  di: Kunze, Tarek, et al.
  Pubblicazione: (2025)
• An open-source voice type classifier for child-centered daylong recordings
  di: Lavechin, Marvin, et al.
  Pubblicazione: (2020)
• BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
  di: Lavechin, Marvin, et al.
  Pubblicazione: (2023)