# The Learning Objective Governs Perceptual Narrowing: A Cross-Lingual, Layer-Wise, Ten-Seed Study of Self-Supervised Speech Encoders

arXiv: https://arxiv.org/abs/2608.00507 · HTML: https://mlsanity.com/paper/2608.00507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Nested Learning: The Illusion of Deep Learning Architectures](https://mlsanity.com/paper/2512.24695/) (2025)
- [Do self-supervised speech models develop human-like perception biases?](https://mlsanity.com/paper/2205.15819/) (2022)
- [Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors](https://mlsanity.com/paper/2603.08359/) (2026)

## Abstract (arXiv)

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.