2026/08/01 by Sejin Yoo
Computer Science · Engineering · #cs.CL #eess.AS
11 pages, 6 figures
arxiv created 2026/08/01 · arxiv updated 2026/08/04
Perceptual narrowing---the developmental loss of non-native phoneme discrimination in the first year of life \citepwerker1984---is a canonical developmental finding, yet what learning objective produces it remains open. We train a \(∼\)7 M-parameter Transformer encoder on child-directed and read speech and evaluate phoneme ABX in English, French, and Mandarin over ten seeds, the seed as the unit of replication. Six results. (1)~The objective sets the direction of cross-lingual transfer: reconstruction (masked mel-prediction) degrades non-native discrimination, prediction (frame-contrastive) improves it---a same-encoder, same-data gap of \(+0.051\) in first-layer Mandarin ABX (\(p=3×10-8\)), unanimous in sign across twenty runs. (2)~That decline combines a large arm-intrinsic difficulty gradient with a smaller language-specialization effect (matched vs. mismatched \(+0.022\), \(p=10-4\), all four layers). (3)~Against a language-symmetric raw-mel floor, reconstruction pushes the first layer below the discriminability of its input; prediction pushes it above. (4)~Read speech gives a \(3.6×\) steeper non-native decline than child-directed speech. (5)~The customary three-seed budget cannot see this reliably: an effect unambiguous at ten seeds is called significant by as few as 70% of three-seed subsets. (6)~Six objective configurations---sharpening, compression, consolidation, their composition, and word-level semantic grounding in two forms---fail to produce the full developmental signature (native improves and non-native declines): a single objective moves both languages the same way because it acts on a shared representation. We conclude that the objective, not the architecture, is the first-order determinant of narrowing-shaped representational change.