Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment

TL;DR

This paper introduces a novel loss function called PCO loss for automatic pronunciation assessment that enhances phonemic distinctions while respecting proficiency level order, improving model performance.

Contribution

The paper proposes the PCO loss, combining phonemic contrast and ordinal regression, to better preserve phoneme distinctions in proficiency prediction models.

Findings

PCO loss improves phoneme discrimination in models.

Enhanced performance on speechocean762 benchmark.

Better alignment with phonemic and proficiency level distinctions.

Abstract

Automatic pronunciation assessment (APA) manages to quantify the pronunciation proficiency of a second language (L2) learner in a language. Prevailing approaches to APA normally leverage neural models trained with a regression loss function, such as the mean-squared error (MSE) loss, for proficiency level prediction. Despite most regression models can effectively capture the ordinality of proficiency levels in the feature space, they are confronted with a primary obstacle that different phoneme categories with the same proficiency level are inevitably forced to be close to each other, retaining less phoneme-discriminative information. On account of this, we devise a phonemic contrast ordinal (PCO) loss for training regression-based APA models, which aims to preserve better phonemic distinctions between phoneme categories meanwhile considering ordinal relationships of the regression target output. Specifically, we introduce a phoneme-distinct regularizer into the MSE loss, which encourages feature representations of different phoneme categories to be far apart while simultaneously pulling closer the representations belonging to the same phoneme category by means of weighted distances. An extensive set of experiments carried out on the speechocean762 benchmark dataset suggest the feasibility and effectiveness of our model in relation to some existing state-of-the-art models.