Mispronunciation Detection and Diagnosis

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

X-MDD: LLM-Based Mispronunciation Detection and Diagnosis for Unseen Languages with Canonical References
Oct 16, 2026Xintong Wang, Junchuan Zhao, Ye WangMispronunciation Detection and Diagnosis Speech Processing
School of Computing, National University of Singapore
Subphonetic Acoustic Modeling via Optimal Transport for Pronunciation Assessment
Sep 12, 2026Haopeng Geng, Jiun-Ting Li, Daisuke Saito +1Mispronunciation Detection and Diagnosis Automated Spoken Language Assessment
Graduate School of Engineering, The University of Tokyo, Japan · Advanced Technology Laboratory, Chunghwa Telecom Co., Ltd., Taiwan
Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant
Jun 23, 2026Milosz Dudek, Daria Hemmerling, Kamil Kwarciak +9Child Speech Recognition Mispronunciation Detection and Diagnosis
AGH University of Krakow, Cracow, Poland · SoftServe, Cracow, Poland · Department of Biomedical Engineering, Silesian University of Technology, Poland +1
A Fusion-Aware Two-Stage Framework for Mispronunciation Detection and Diagnosis in Low-Resource Modern Standard Arabic
Jun 23, 2026Jing Yang, Shuqing Zhang, Yongyi Deng +5Domain Adaptation Mispronunciation Detection and Diagnosis
School of Electronic Information, Wuhan University, Wuhan Hubei, 430072, China · School of Computing and Information Systems, University of Melbourne, Melbourne, Australia · Northwestern Polytechnical University +1
Using Phonological-Level Wav2Vec2 for Mandarin Automatic Mispronunciation Detection and Diagnosis
Jun 20, 2026Jinghao Chen, Mostafa Shahin, Beena AhmedMispronunciation Detection and Diagnosis Speech Processing
School of Electrical Engineering and Telecommunications, UNSW, Australia
Domain-Aware Mispronunciation Detection and Diagnosis Using Language-Specific Statistical Graphs
Jun 4, 2026Huu Tuong Tu, Hanh Nguyen, Thien Van Luong +3Mispronunciation Detection and Diagnosis Speech Processing
1Hanoi University of Science and Technology · 2VNPT AI, VNPT Group · 3National Economics University
Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis
Apr 24, 2026Haopeng Geng, Longfei Yang, Xi Chen +3Mispronunciation Detection and Diagnosis Speech Processing
Graduate School of Engineering, The University of Tokyo, Japan
IQRA 2026: Interspeech Challenge on Automatic Pronunciation Assessment for Modern Standard Arabic (MSA)
Mar 31, 2026Yassine El Kheir, Amit Meghanani, Mostafa Shahin +5Mispronunciation Detection and Diagnosis Automated Spoken Language Assessment
DFKI & Technical University of Berlin, Germany · University of Sheffield, UK · University of New South Wales, Australia +4

Oct 16, 2026J/K move · Enter open · S save

X-MDD: LLM-Based Mispronunciation Detection and Diagnosis for Unseen Languages with Canonical References

Xintong Wang, Junchuan Zhao, Ye Wang

School of Computing, National University of Singapore

Mispronunciation Detection and Diagnosis Speech Processing Automated Spoken Language Assessment

Open paper AskPDF arXiv

Mispronunciation detection and diagnosis (MDD) provides phone-level feedback to language learners, but extending it to new languages typically requires collecting and annotating learner speech for each target language. This repeated annotation effort is costly and limits the language coverage of pronunciation feedback. We study whether MDD capabilities learned from annotated learner speech can be applied to languages unseen during MDD training when canonical pronunciation references are available. Our multilingual LLM-based model, X-MDD, uses canonical speech and phones as references to predict the phone sequence actually produced by a learner. It incorporates in-context demonstrations for inference-time adaptation and is further optimized with group relative policy optimization (GRPO) using detection F1 and phone error rate. We further analyze how canonical inputs affect prediction and find that (1) canonical speech and phones jointly contribute to actual-phone prediction, and (2) conflicting speech evidence reduces the tendency to copy canonical phones. Trained only on Mandarin and English, X-MDD achieves a detection F1 of 38.07 on Arabic Qur'anic recitation, compared with 44.14 for a supervised challenge baseline trained on Arabic. It also achieves F1 scores of 78.68 and 58.78 on Mandarin and English, respectively, demonstrating effective multilingual MDD within a single model.