A statistical model for word discovery in child directed speech

TL;DR

This paper introduces a statistical model and an incremental unsupervised algorithm for segmenting and discovering words in child-directed speech, demonstrating competitive performance through empirical testing.

Contribution

It presents a novel statistical model and an incremental learning algorithm for word discovery in child speech, outperforming existing models in similar tasks.

Findings

The algorithm effectively segments child speech into words.

Empirical results show competitive performance with existing models.

The model advances unsupervised word discovery methods.

Abstract

A statistical model for segmentation and word discovery in child directed speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described and results of empirical tests showing that the algorithm is competitive with other models that have been used for similar tasks are also presented.