Evaluating Logit-Based GOP Scores for Mispronunciation Detection
Abstract
Pronunciation assessment relies on goodness of pronunciation (GOP) scores, traditionally derived from softmax-based posterior probabilities. However, posterior probabilities may suffer from overconfidence and poor phoneme separation, limiting their effectiveness. This study compares logit-based GOP scores with probability-based GOP scores for mispronunciation detection. We conducted our experiment on two L2 English speech datasets spoken by Dutch and Mandarin speakers, assessing classification performance and correlation with human ratings. Logit-based methods outperform probability-based GOP in classification, but their effectiveness depends on dataset characteristics. The maximum logit GOP shows the strongest alignment with human perception, while a combination of different GOP scores balances probability and logit features. The findings suggest that hybrid GOP methods incorporating uncertainty modeling and phoneme-specific weighting improve pronunciation assessment.
Cite
@article{arxiv.2506.12067,
title = {Evaluating Logit-Based GOP Scores for Mispronunciation Detection},
author = {Aditya Kamlesh Parikh and Cristian Tejedor-Garcia and Catia Cucchiarini and Helmer Strik},
journal= {arXiv preprint arXiv:2506.12067},
year = {2025}
}
Comments
Accepted to Interspeech 2025. This publication is part of the project Responsible AI for Voice Diagnostics (RAIVD) with file number NGF.1607.22.013 of the research programme NGF AiNed Fellowship Grants which is financed by the Dutch Research Council (NWO)