Host: The Japanese Society for Artificial Intelligence
Name : 34th Annual Conference, 2020
Number : 34
Location : Online
Date : June 09, 2020 - June 12, 2020
Infants need to segment their native language into phonemes and words at the same time without supervision. Taniguchi, Nagasaka, & Nakashima (2016) showed that Nonparametric Bayesian Double Articulation Analyzer could analyze latent double articulation structure, i.e., hierarchically organized latent words and phonemes, of utterance data consisting of a limited vocabulary in an unsupervised manner by assuming hierarchical Dirichlet process hidden language model (HDP-HLM). In this study, we attempted unsupervised double articulation analysis of natural speech in a video game environment and tried to give meaning to the segmented words. The result of an experiment demonstrated that the utterances were roughly correctly segmented, and the meanings of up, down, left and right were almost correctly learned.