Enhancing GOP in CTC-Based Mispronunciation Detection with Phonological Knowledge
This work addresses efficiency and accuracy issues in computer-assisted pronunciation training systems for language learners, but it is incremental as it builds on existing alignment-free methods.
The paper tackled the problem of improving the goodness of pronunciation (GOP) metric in mispronunciation detection by introducing a substitution-aware alignment-free method that restricts phoneme substitutions based on clusters and learner errors, resulting in outperformance over baseline methods on L2 English speech datasets.
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.