Evaluation different non-native pronunciation scoring metrics with the Japanese speakers of the sample corpus

Abstract

This work presents an analysis over the set of results derived from the goodness of pronunciation (GOP) algorithm for the evaluation of pronunciation at phoneme level over the SAMPLE corpus of non native speech. This corpus includes several recordings of uttered sentences by distinct speakers that have been rated in terms of quality by a group of linguists. The utterances have been automatically rated with the GOP algorithm. The phoneme dependence is discussed to suggest the normalization of intermediate results that could enhance the metrics performance. As result, new scoring proposals are presented which are based on computing the log-likelihood values obtained from the GOP algorithm and the application of a set of rules. These new scores show to correlate with the human rates better than the original GOP metric.