用小模型模拟婴儿学语言，揭示关键期听力变化机制
Developmental Predictive Coding Model for Early Infancy Mono and Bilingual Vocal Continual Learning
- 基于预测编码的持续学习框架，支持单语和双语语音学习
- 后期接触第二语言时出现感知窄化，符合人类发展规律
- 模型轻量可解释，适合研究语言习得关键期
理解婴儿如何感知语音和语言结构仍是开放问题。以往人工神经网络研究多依赖大规模数据生成模型，旨在复现如‘感知窄化’等语言现象。本文提出一种小型生成神经网络，结合基于预测编码的持续学习机制，用于模拟单语与双语语音在‘关键期’的语言声音习得，以及无学习参与的后期语音模仿（即组合优化生成）。该模型强调可解释性，体现在线学习优势：无需大量离线训练，能随新数据持续更新，对输入变化具有适应性与响应性。实验表明，若第二语言学习发生在后期婴儿期，其挑战显著加剧，重现了感知窄化效应。
原文摘要 · Abstract (English)
Understanding how infants perceive speech sounds and language structures is still an open problem. Previous research in artificial neural networks has mainly focused on large dataset-dependent generative models, aiming to replicate language-related phenomena such as ''perceptual narrowing''. In this paper, we propose a novel approach using a small-sized generative neural network equipped with a continual learning mechanism based on predictive coding for mono-and bilingual speech sound learning (referred to as language sound acquisition during ''critical period'') and a compositional optimization mechanism for generation where no learning is involved (later infancy sound imitation). Our model prioritizes interpretability and demonstrates the advantages of online learning: Unlike deep networks requiring substantial offline training, our model continuously updates with new data, making it adaptable and responsive to changing inputs. Through experiments, we demonstrate that if second language acquisition occurs during later infancy, the challenges associated with learning a foreign language after the critical period amplify, replicating the perceptual narrowing effect.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。