Filtering by topic mispronunciation-detection(1)Clear all filters

• Paper·arXiv — Language & NLP (cs.CL)·4 Jun 2026

  Domain-Aware Mispronunciation Detection and Diagnosis Using Language-Specific Statistical Graphs

  Huu Tuong Tu, Hanh Nguyen, Thien Van Luong, Nguyen Tien Cuong et al.

  A method using statistical graphs to model phoneme confusion patterns is proposed for mispronunciation detection and diagnosis, with a language-specific strategy to capture systematic pronunciation differences across native language backgrounds. The approach achieves an F1-score of 59.52% on the L2-ARCTIC benchmark, outperforming several competitive baselines.

  Original abstract

  Mispronunciation Detection and Diagnosis (MDD) has gained increasing importance in computer-assisted language learning and speech technology in recent years. In this paper, we propose a method for constructing statistical graphs that enable models to learn phoneme confusion patterns represented as directed graphs. Furthermore, we introduce a language-specific strategy to capture systematic pronunciation differences across various native language (L1) backgrounds. The effectiveness of our approach is demonstrated through extensive experiments on the L2-ARCTIC benchmark, where it achieves an F1-score of 59.52%, outperforming several competitive baselines.

  mispronunciation-detectioncomputer-assisted-language-learningspeech-recognitionl2-phonology★ 8/10