Enhancing GOP in CTC-Based Mispronunciation Detection with Phonological Knowledge

TL;DR

This paper proposes a substitution-aware, alignment-free GOP method for mispronunciation detection that improves efficiency and accuracy by restricting phoneme substitutions based on phonological knowledge.

Contribution

It introduces a novel substitution-aware alignment-free GOP approach that leverages phonological knowledge to enhance mispronunciation detection performance.

Findings

RPS setup outperforms baseline in accuracy

Alignment-free methods are more efficient than traditional GOP

Phonological restrictions improve detection robustness

Abstract

Computer-Assisted Pronunciation Training (CAPT) systems employ automatic measures of pronunciation quality, such as the goodness of pronunciation (GOP) metric. GOP relies on forced alignments, which are prone to labeling and segmentation errors due to acoustic variability. While alignment-free methods address these challenges, they are computationally expensive and scale poorly with phoneme sequence length and inventory size. To enhance efficiency, we introduce a substitution-aware alignment-free GOP that restricts phoneme substitutions based on phoneme clusters and common learner errors. We evaluated our GOP on two L2 English speech datasets, one with child speech, My Pronunciation Coach (MPC), and SpeechOcean762, which includes child and adult speech. We compared RPS (restricted phoneme substitutions) and UPS (unrestricted phoneme substitutions) setups within alignment-free methods, which outperformed the baseline. We discuss our results and outline avenues for future research.