Prosodic Features from Large Corpora of Child-Directed Speech as Predictors of the Age of Acquisition of Words

TL;DR

This study introduces a large corpus of child-directed speech with prosodic features and demonstrates that these features improve models predicting the age at which children acquire words.

Contribution

The paper presents a large-scale, multi-modal corpus with automatically extracted prosodic features and shows their effectiveness in predicting word acquisition age.

Findings

Prosodic features improve prediction accuracy of word age of acquisition.

Prosody enhances multi-modal language models for child speech.

Corpus provides a valuable resource for future research.

Abstract

The impressive ability of children to acquire language is a widely studied phenomenon, and the factors influencing the pace and patterns of word learning remains a subject of active research. Although many models predicting the age of acquisition of words have been proposed, little emphasis has been directed to the raw input children achieve. In this work we present a comparatively large-scale multi-modal corpus of prosody-text aligned child directed speech. Our corpus contains automatically extracted word-level prosodic features, and we investigate the utility of this information as predictors of age of acquisition. We show that prosody features boost predictive power in a regularized regression, and demonstrate their utility in the context of a multi-modal factorized language models trained and tested on child-directed speech.