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

• URL: http://arxiv.org/abs/2608.00507v1
• Date: Sat, 01 Aug 2026 08:02:35 GMT
• Title: The Learning Objective Governs Perceptual Narrowing: A Cross-Lingual, Layer-Wise, Ten-Seed Study of Self-Supervised Speech Encoders
• Abstract summary: We train a Transformer encoder on child-directed and read speech and evaluate phoneme ABX in English, French, and Mandarin over ten seeds.<n>We conclude that the objective, not the architecture, is the first-order determinant of narrowing-shaped representational change.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Perceptual narrowing---the developmental loss of non-native phoneme discrimination in the first year of life \citep{werker1984}---is a canonical developmental finding, yet \emph{what learning objective produces it} remains open. We train a \(\sim\)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. \textbf{(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 (\(p=3\times10^{-8}\)), unanimous in sign across twenty runs. \textbf{(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). \textbf{(3)}~Against a language-symmetric raw-mel floor, reconstruction pushes the first layer \emph{below} the discriminability of its input; prediction pushes it \emph{above}. \textbf{(4)}~Read speech gives a \(3.6\times\) steeper non-native decline than child-directed speech. \textbf{(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. \textbf{(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 \emph{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.

Related papers

• Write-Protected Discrete Bottlenecks for Language-Grounded World Models: A Structural Limitation and Sufficient Fix [0.0]
  We characterize a sufficient set of three constraints that prevent the failure of a Gumbel-softmax-based discrete symbol bottleneck.<n>We demonstrate zero symbol collapse in all 32 seeds, with the blackboard achieving 79-100% semantic binding across three encoder architectures.
  arXiv  Detail & Related papers  (2026-07-09T09:55:17Z)
• DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation [20.845447775728545]
  Large language models increasingly emphunderstand dialectal English, yet still emphproduce only standard, US-leaning English.<n>We introduce textbfDiaLLM, which continually pretrains three open-weight language model families on the International Corpus of English.
  arXiv  Detail & Related papers  (2026-07-08T17:24:27Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Language-Conditioned Visual Grounding with CLIP Multilingual [0.0]
  Cross-language divergence could arise from the visual encoder, the text branch, or their interaction.<n>We resolve this ambiguity through a dense multilingual CLIP probe in which the visual encoder is held identical across thirteen typologically diverse languages.
  arXiv  Detail & Related papers  (2026-05-09T17:06:16Z)
• Bilingual Text-to-Motion Generation: A New Benchmark and Baselines [52.71312720094036]
  We introduce BiHumanML3D, the first bilingual text-to-motion benchmark, constructed via LLM-assisted annotation and rigorous manual correction.<n>We also propose a simple yet effective baseline, Bilingual Motion Diffusion synthesis (BiMD), featuring Cross-Lingual Alignment (CLA)<n>BiMD with CLA achieves an FID of 0.045 vs. 0.169 and R@3 of 82.8% vs. 80.8%, significantly outperforms monolingual diffusion models and translation baselines on BiHumanML3D.
  arXiv  Detail & Related papers  (2026-03-26T08:48:27Z)
• Beyond Cosine Similarity: Taming Semantic Drift and Antonym Intrusion in a 15-Million Node Turkish Synonym Graph [0.0]
  We build a large-scale semantic clustering system specifically designed to tackle this problem head on.<n>We introduce a labeled dataset of 843,000 concept pairs spanning synonymy, antonymy, and co-hyponymy.<n>Second, we propose a specialized three-way semantic relation discriminator that achieves 90% macro-F1.<n>Third, we introduce a novel soft-to-hard clustering algorithm that mitigates semantic drift while simultaneously resolving polysemy.
  arXiv  Detail & Related papers  (2026-01-19T17:37:25Z)
• Fundamental Principles of Linguistic Structure are Not Represented by o3 [3.335047764053173]
  o3 model fails to generalize basic phrase structure rules.<n>It fails to correctly rate and explain acceptability dynamics.<n>It fails to distinguish between instructions to generate unacceptable semantic vs. unacceptable syntactic outputs.
  arXiv  Detail & Related papers  (2025-02-15T23:53:31Z)
• Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics [50.982315553104975]
  We investigate the bottom-up evolution of lexical semantics for a popular large language model, namely Llama2. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics.
  arXiv  Detail & Related papers  (2024-03-03T13:14:47Z)
• Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents [61.63208012250885]
  We formulate recognizing semantic differences as a token-level regression task. We study three unsupervised approaches that rely on a masked language model. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels.
  arXiv  Detail & Related papers  (2023-05-22T17:58:04Z)
• VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning [56.47303426167584]
  We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
  arXiv  Detail & Related papers  (2023-04-17T12:23:41Z)
• Pairwise Supervised Contrastive Learning of Sentence Representations [20.822509446824125]
  PairSupCon aims to bridge semantic entailment and contradiction understanding with high-level categorical concept encoding. We evaluate it on various downstream tasks that involve understanding sentence semantics at different granularities.
  arXiv  Detail & Related papers  (2021-09-12T04:12:16Z)
• Semantic-Preserving Adversarial Text Attacks [85.32186121859321]
  We propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models. Our method achieves the highest attack success rates and semantics rates by changing the smallest number of words compared with existing methods.
  arXiv  Detail & Related papers  (2021-08-23T09:05:18Z)
• Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing [55.97957664897004]
  An effective recipe for building seq2seq, non-autoregressive, task-orienteds to map utterances to semantic frames proceeds in three steps. These models are typically bottlenecked by length prediction. In our work, we propose non-autoregressives which shift the decoding task from text generation to span prediction.
  arXiv  Detail & Related papers  (2021-04-15T07:02:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.