Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis

2026-04-23

AI Summary

This work addresses limitations in existing ASR-based mispronunciation detection methods, which struggle to capture transient pronunciation deviations due to the coarse-grained nature of CTC alignment and suffer from prediction bias when explicitly incorporating canonical pronunciation priors. To overcome these issues, the authors propose a prompt-free decoupled framework that separates acoustic modeling from canonical pronunciation guidance. Specifically, they introduce the CROTTC model to achieve frame-level monotonic alignment for precise deviation localization and integrate an implicit feedback (IF) strategy to inject mispronunciation knowledge without inducing linguistic bias. Evaluated on the L2-ARCTIC and Iqra'Eval2 datasets, the proposed approach achieves F1-scores of 71.77% and 71.70%, respectively, demonstrating significantly improved robustness and accuracy in mispronunciation detection.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Mispronunciation Detection and Diagnosis (MDD) requires modeling fine-grained acoustic deviations. However, current ASR-derived MDD systems often face inherent limitations. In particular, CTC-based models favor sequence-level alignments that neglect transient mispronunciation cues, while explicit canonical priors bias predictions toward intended targets. To address these bottlenecks, we propose a prompt-free framework decoupling acoustic fidelity from canonical guidance. First, we introduce CROTTC, an acoustic model enforcing monotonic, frame-level alignment to accurately capture pronunciation deviations. Second, we implicitly inject mispronunciation information via the IF strategy under the knowledge transfer principle. Experiments show CROTTC-IF achieves a 71.77% F1-score on L2-ARCTIC and 71.70% F1-score on the Iqra'Eval2 leaderboard. With empirical analysis, we demonstrate that decoupling acoustics from explicit priors provides highly robust MDD.

Problem

• Mispronunciation Detection and Diagnosis
• Acoustic Sparsity
• Linguistic Bias
• CTC-based Models
• Canonical Priors

Innovation

• prompt-free
• mispronunciation detection
• frame-level alignment
• acoustic decoupling
• implicit feedback