A model of early word acquisition based on realistic-scale audiovisual naming events

TL;DR

This study presents a model that simulates infant early word learning through statistical regularities in audiovisual input, demonstrating effective vocabulary acquisition without prior linguistic knowledge.

Contribution

The paper introduces a realistic-scale audiovisual model that learns word-object associations from raw sensory data, matching infant vocabulary growth rates.

Findings

Model successfully recognizes words and associates them with objects

Vocabulary growth rate aligns with infant development

Supports statistical learning as a mechanism for early word perception

Abstract

Infants gradually learn to parse continuous speech into words and connect names with objects, yet the mechanisms behind development of early word perception skills remain unknown. We studied the extent to which early words can be acquired through statistical learning from regularities in audiovisual sensory input. We simulated word learning in infants up to 12 months of age in a realistic setting, using a model that solely learns from statistical regularities in unannotated raw speech and pixel-level visual input. Crucially, the quantity of object naming events was carefully designed to match that accessible to infants of comparable ages. Results show that the model effectively learns to recognize words and associate them with corresponding visual objects, with a vocabulary growth rate comparable to that observed in infants. The findings support the viability of general statistical learning for early word perception, demonstrating how learning can operate without assuming any prior linguistic capabilities.