A model of early word acquisition based on realistic-scale audiovisual naming events
This addresses the unknown mechanisms of early word acquisition in infants, demonstrating the viability of statistical learning without prior linguistic assumptions, though it is incremental as it builds on existing statistical learning theories.
The study tackled the problem of how infants acquire early word perception skills by simulating word learning through statistical regularities in unannotated audiovisual input, showing that the model effectively learns words and associates them with objects with a vocabulary growth rate comparable to infants.
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.