Lost but not erased: Finding traces of a forgotten language in neural speech models

arXiv:2608.25976v1 Announce Type: new Abstract: International adoptees retain phonological traces of a birth language they can no longer speak or comprehend, a persistence typically attributed to a biologically-timed critical period. We asked whether it could instead reflect the ordinary dynamics of learning, using automatic speech recognition models that simulate the international adoptee experience without maturational confounds. Models were trained on one language and then abruptly switched to a second. We found that traces of the first language persisted throughout second-language training, but mainly in the lowest, pre-phonemic layers. These traces were functional, as models with early exposure re-learned their lost first language 14% faster than naive models; this advantage held even against models adopted early from a related language and disappeared when the earliest layers were substituted from a non-adopted model. We argue that these critical-period effects reflect entrenchment of foundational representations rather than a maturational loss of plasticity, and that experience plays a central role in critical periods in language acquisition.

Related

• Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
• Easper: An Accessible ASR Pipeline for Language Documentation
• Self-Supervised Speech Representations Track Spoken Language Convergence to Adult Models in Infants and Children Who Are Deaf/Hard-of-Hearing

Source: arXiv cs.CL | 2026-08-27