IQRA 2026: Interspeech Challenge on Automatic Assessment Pronunciation for Modern Standard Arabic (MSA)

2026-03-30

AI Summary

This study addresses the challenges of scarce authentic error data and insufficient evaluation accuracy in mispronunciation detection and diagnosis (MDD) for Modern Standard Arabic (MSA) by organizing the second IQRA International Challenge. The work introduces the new dataset Iqra_Extra_IS26 and proposes innovative approaches, including a CTC-based self-supervised learning model, a two-stage fine-tuning strategy, and large audio-language models. Compared to the first challenge, the proposed system achieves a substantial improvement of 0.28 in F1-score, demonstrating that high-quality data combined with advanced modeling strategies significantly enhances MDD performance for Arabic. These contributions effectively advance the maturity and development of research in this domain.

Abstract

We present the findings of the second edition of the IQRA Interspeech Challenge, a challenge on automatic Mispronunciation Detection and Diagnosis (MDD) for Modern Standard Arabic (MSA). Building on the previous edition, this iteration introduces \textbf{Iqra\_Extra\_IS26}, a new dataset of authentic human mispronounced speech, complementing the existing training and evaluation resources. Submitted systems employed a diverse range of approaches, spanning CTC-based self-supervised learning models, two-stage fine-tuning strategies, and using large audio-language models. Compared to the first edition, we observe a substantial jump of \textbf{0.28 in F1-score}, attributable both to novel architectures and modeling strategies proposed by participants and to the additional authentic mispronunciation data made available. These results demonstrate the growing maturity of Arabic MDD research and establish a stronger foundation for future work in Arabic pronunciation assessment.

Problem

• Mispronunciation Detection and Diagnosis
• Modern Standard Arabic
• Automatic Pronunciation Assessment
• Speech Recognition
• Pronunciation Errors

Innovation

• Mispronunciation Detection and Diagnosis
• Modern Standard Arabic
• Self-supervised Learning
• Audio-Language Models
• Iqra_Extra_IS26