Evaluating computational models of infant phonetic learning across languages
This work addresses the challenge of understanding early phonetic learning mechanisms for developmental psychology and computational linguistics, but it is incremental as it builds on prior models.
The study tackled the problem of predicting infant phonetic learning from speech input by evaluating five computational models on three phone contrasts across languages, finding varying degrees of agreement with infants' discrimination patterns.
In the first year of life, infants' speech perception becomes attuned to the sounds of their native language. Many accounts of this early phonetic learning exist, but computational models predicting the attunement patterns observed in infants from the speech input they hear have been lacking. A recent study presented the first such model, drawing on algorithms proposed for unsupervised learning from naturalistic speech, and tested it on a single phone contrast. Here we study five such algorithms, selected for their potential cognitive relevance. We simulate phonetic learning with each algorithm and perform tests on three phone contrasts from different languages, comparing the results to infants' discrimination patterns. The five models display varying degrees of agreement with empirical observations, showing that our approach can help decide between candidate mechanisms for early phonetic learning, and providing insight into which aspects of the models are critical for capturing infants' perceptual development.