Self-Supervised Speech Representations Track Spoken Language Convergence to Adult Models in Infants and Children Who Are Deaf/Hard-of-Hearing

The study demonstrates that self‑supervised speech embeddings can track how children’s speech converges toward adult patterns over development. Using HuBERT‑BASE embeddings extracted from over 925 hours of child‑caregiver recordings, the researchers found that the acoustic distance between a child’s vocalizations and those of their female caregiver decreased with the child’s hearing age, even after controlling for pitch and vocalization length. This single distance metric also correlated with several standardized speech and language assessments from infancy through preschoolhood, suggesting a scalable, language‑neutral way to monitor spoken language development in everyday settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• rag