A Neural Model for Word Repetition

2025-06-16

AI Summary

Current computational models of language production lack interpretability and neurobiological plausibility, hindering mechanistic understanding of speech errors in word repetition tasks. Method: We developed the first cognitively grounded, interpretable deep neural network integrating hierarchical cognitive architecture with systematic behavioral paradigms and neuron-level ablation (simulating focal brain lesions). Our approach combines model training, construction of multidimensional behavioral test sets, cross-modal alignment of human and model responses, and targeted ablation analysis. Results: The model successfully reproduces key human phenomena—including phonemic similarity errors and word-frequency effects—and establishes the first principled mapping between artificial lesion profiles and clinical speech disorders (e.g., aphasia). It further reveals fundamental limitations of existing models in temporal robustness and lesion-specific error patterns. This work bridges computational modeling and neurolinguistics via a causally interpretable, neurocomputationally constrained framework.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

It takes several years for the developing brain of a baby to fully master word repetition-the task of hearing a word and repeating it aloud. Repeating a new word, such as from a new language, can be a challenging task also for adults. Additionally, brain damage, such as from a stroke, may lead to systematic speech errors with specific characteristics dependent on the location of the brain damage. Cognitive sciences suggest a model with various components for the different processing stages involved in word repetition. While some studies have begun to localize the corresponding regions in the brain, the neural mechanisms and how exactly the brain performs word repetition remain largely unknown. We propose to bridge the gap between the cognitive model of word repetition and neural mechanisms in the human brain by modeling the task using deep neural networks. Neural models are fully observable, allowing us to study the detailed mechanisms in their various substructures and make comparisons with human behavior and, ultimately, the brain. Here, we make first steps in this direction by: (1) training a large set of models to simulate the word repetition task; (2) creating a battery of tests to probe the models for known effects from behavioral studies in humans, and (3) simulating brain damage through ablation studies, where we systematically remove neurons from the model, and repeat the behavioral study to examine the resulting speech errors in the"patient"model. Our results show that neural models can mimic several effects known from human research, but might diverge in other aspects, highlighting both the potential and the challenges for future research aimed at developing human-like neural models.

Problem

• Modeling neural mechanisms of word repetition in humans
• Bridging cognitive models and neural processes via deep learning
• Simulating speech errors from brain damage through ablation studies

Innovation

• Deep neural networks model word repetition
• Ablation studies simulate brain damage effects
• Behavioral tests compare models to humans