|
|
<!doctype html> |
|
|
<html lang="en"> |
|
|
<head> |
|
|
<meta charset="utf-8" /> |
|
|
<meta name="viewport" content="width=device-width" /> |
|
|
<title>Iqra’Eval Shared Task</title> |
|
|
<style> |
|
|
:root { |
|
|
--navy-blue: #001f4d; |
|
|
--coral: #ff6f61; |
|
|
--light-gray: #f5f7fa; |
|
|
--text-dark: #222; |
|
|
} |
|
|
body { |
|
|
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; |
|
|
background-color: var(--light-gray); |
|
|
color: var(--text-dark); |
|
|
margin: 20px; |
|
|
line-height: 1.6; |
|
|
} |
|
|
h1, h2, h3 { |
|
|
color: var(--navy-blue); |
|
|
font-weight: 700; |
|
|
margin-top: 1.2em; |
|
|
} |
|
|
h1 { |
|
|
text-align: center; |
|
|
font-size: 2.8rem; |
|
|
margin-bottom: 0.3em; |
|
|
} |
|
|
h2 { |
|
|
border-bottom: 3px solid var(--coral); |
|
|
padding-bottom: 0.3em; |
|
|
} |
|
|
h3 { |
|
|
color: var(--coral); |
|
|
margin-top: 1em; |
|
|
} |
|
|
p, ul, pre { |
|
|
max-width: 900px; |
|
|
margin: 0.8em auto; |
|
|
} |
|
|
ul { padding-left: 1.2em; } |
|
|
ul li { margin: 0.4em 0; } |
|
|
code { |
|
|
background-color: #eef4f8; |
|
|
color: var(--navy-blue); |
|
|
padding: 2px 6px; |
|
|
border-radius: 4px; |
|
|
font-family: Consolas, monospace; |
|
|
font-size: 0.9em; |
|
|
} |
|
|
pre { |
|
|
background-color: #eef4f8; |
|
|
padding: 1em; |
|
|
border-radius: 8px; |
|
|
overflow-x: auto; |
|
|
font-size: 0.95em; |
|
|
} |
|
|
a { |
|
|
color: var(--coral); |
|
|
text-decoration: none; |
|
|
} |
|
|
a:hover { text-decoration: underline; } |
|
|
.card { |
|
|
max-width: 960px; |
|
|
background: white; |
|
|
margin: 0 auto 40px; |
|
|
padding: 2em 2.5em; |
|
|
box-shadow: 0 4px 14px rgba(0,0,0,0.1); |
|
|
border-radius: 12px; |
|
|
} |
|
|
img { |
|
|
display: block; |
|
|
margin: 20px auto; |
|
|
max-width: 100%; |
|
|
height: auto; |
|
|
border-radius: 8px; |
|
|
box-shadow: 0 4px 8px rgba(0,31,77,0.15); |
|
|
} |
|
|
.centered p { |
|
|
text-align: center; |
|
|
font-style: italic; |
|
|
color: var(--navy-blue); |
|
|
margin-top: 0.4em; |
|
|
} |
|
|
.highlight { |
|
|
color: var(--coral); |
|
|
font-weight: 700; |
|
|
} |
|
|
|
|
|
p > ul { margin-top: 0.3em; } |
|
|
</style> |
|
|
</head> |
|
|
<body> |
|
|
<div class="card"> |
|
|
<h1>Iqra’Eval Shared Task</h1> |
|
|
|
|
|
<img src="IqraEval.png" alt="IqraEval Logo" /> |
|
|
|
|
|
<h2>Overview</h2> |
|
|
<p> |
|
|
<strong>Iqra'Eval</strong> is a shared task aimed at advancing <strong>automatic assessment of Qur’anic recitation pronunciation</strong> by leveraging computational methods to detect and diagnose pronunciation errors. The focus on Qur’anic recitation provides a standardized and well-defined context for evaluating Modern Standard Arabic (MSA) pronunciation. |
|
|
</p> |
|
|
<p> |
|
|
Participants will develop systems capable of detecting mispronunciations (e.g., substitution, deletion, or insertion of phonemes). |
|
|
</p> |
|
|
|
|
|
<h2>Timeline</h2> |
|
|
<ul> |
|
|
<li><strong>June 1, 2025</strong>: Official announcement</li> |
|
|
<li><strong>June 10, 2025</strong>: Release of training data, dev set, phonetizer, baselines</li> |
|
|
<li><strong>June 20, 2025</strong>: Opening Leaderboard</li> |
|
|
<li><strong>July 20, 2025</strong>: Registration deadline</li> |
|
|
<li><strong>July 24, 2025</strong>: QuranMB test data release</li> |
|
|
<li><strong>July 29, 2025</strong>: Test set submission closes</li> |
|
|
<li><strong>July 30, 2025</strong>: Final results released</li> |
|
|
<li><strong>August 15, 2025</strong>: System description papers due</li> |
|
|
<li><strong>August 22, 2025</strong>: Notification of acceptance</li> |
|
|
<li><strong>September 5, 2025</strong>: Camera-ready versions due</li> |
|
|
</ul> |
|
|
|
|
|
<h2>Task Description: Quranic Mispronunciation Detection System</h2> |
|
|
<p> |
|
|
Design a model to detect and provide detailed feedback on mispronunciations in Quranic recitations. Users read vowelized verses; the model predicts the spoken phoneme sequence and flags deviations. Evaluation is on the <strong>QuranMB.v2</strong> dataset with human‐annotated errors. |
|
|
</p> |
|
|
<div class="centered"> |
|
|
<img src="task.png" alt="System Overview" /> |
|
|
<p>Figure: Overview of the Mispronunciation Detection Workflow</p> |
|
|
</div> |
|
|
|
|
|
<h3>1. Read the Verse</h3> |
|
|
<p> |
|
|
System shows a <strong>Reference Verse</strong> plus its <strong>Reference Phoneme Sequence</strong>. |
|
|
</p> |
|
|
<p><strong>Example:</strong></p> |
|
|
<ul> |
|
|
<li><strong>Arabic:</strong> إِنَّ الصَّفَا وَالْمَرْوَةَ مِنْ شَعَائِرِ اللَّهِ</li> |
|
|
<li> |
|
|
<strong>Phoneme:</strong> |
|
|
<code>< i n n a SS A f aa w a l m a r w a t a m i n $ a E a a < i r i l l a h i</code> |
|
|
</li> |
|
|
</ul> |
|
|
|
|
|
<h3>2. Save Recording</h3> |
|
|
<p> |
|
|
User recites; system captures and stores the audio waveform. |
|
|
</p> |
|
|
|
|
|
<h3>3. Mispronunciation Detection</h3> |
|
|
<p> |
|
|
Model predicts the phoneme sequence—deviations from reference indicate mispronunciations. |
|
|
</p> |
|
|
<p><strong>Example of Mispronunciation:</strong></p> |
|
|
<ul> |
|
|
<li><strong>Reference:</strong> <code>< i n n a SS A f aa w a l m a r w a t a m i n $ a E a a < i r i l l a h i</code></li> |
|
|
<li><strong>Predicted:</strong> <code>< i n n a SS A f aa w a l m a r w a t a m i n s a E a a < i r u l l a h i</code></li> |
|
|
<li> |
|
|
<strong>Annotated:</strong> |
|
|
<code>< i n n a SS A f aa w a l m a r w <span class="highlight">s</span> a E a a < i <span class="highlight">r u</span> l l a h i</code> |
|
|
</li> |
|
|
</ul> |
|
|
<p> |
|
|
Here, <code>$</code>→<code>s</code> and <code>i</code>→<code>u</code>; omission of <code>ta</code> went undetected. |
|
|
</p> |
|
|
|
|
|
<h2>Phoneme Set Description</h2> |
|
|
<p> |
|
|
The phoneme set used in this work is based on a specialized phonetizer developed for vowelized MSA by Nawar Halabi. It includes a comprehensive range of 68 phonemes designed to capture key phonetic and prosodic features of Qur’an recitation, such as stress, pausing, intonation, emphaticness, and notably, gemination. Gemination—the doubling of consonant sounds—is explicitly represented by duplicating the consonant symbol (e.g., <code>/b/</code> becomes <code>/bb/</code>). |
|
|
While the phonetizer distinguishes vowels following emphatic and non-emphatic consonants, this distinction is merged in our approach to better align with MSA pronunciation norms, where the difference does not affect meaning. This phoneme set provides a detailed yet practical representation of the speech sounds relevant for accurate mispronunciation detection in Qur’anic recitation. |
|
|
For further details, including the full phoneme inventory, see <a href="https://huggingface.co/spaces/IqraEval/ArabicPhoneme">Phoneme Inventory</a>. |
|
|
</p> |
|
|
|
|
|
<h2>Training Dataset: Description</h2> |
|
|
<p> |
|
|
Hosted on Hugging Face: |
|
|
</p> |
|
|
<ul> |
|
|
<li> |
|
|
<strong>Training:</strong> 79 hours of MSA speech augmented with Qur’anic recitations |
|
|
<code>load_dataset("IqraEval/Iqra_train", split="train")</code> |
|
|
</li> |
|
|
<li> |
|
|
<strong>Development:</strong> 3.4 hours as dev set |
|
|
<code>load_dataset("IqraEval/Iqra_train", split="dev")</code> |
|
|
</li> |
|
|
</ul> |
|
|
<p> |
|
|
<strong>Columns:</strong> |
|
|
<ul> |
|
|
<li><code>audio</code>: waveform</li> |
|
|
<li><code>sentence</code>: original text (verse)</li> |
|
|
<li><code>index</code>: verse ID</li> |
|
|
<li><code>tashkeel_sentence</code>: fully diacritized text (verse)</li> |
|
|
<li><code>phoneme</code>: phoneme sequence (using phonetizer)</li> |
|
|
</ul> |
|
|
</p> |
|
|
|
|
|
<h2>Training Dataset: TTS Data (Optional)</h2> |
|
|
<p> |
|
|
Auxiliary high-quality TTS corpus for augmentation: |
|
|
<code>load_dataset("IqraEval/Iqra_TTS")</code> |
|
|
</p> |
|
|
|
|
|
<h2>Test Dataset: QuranMB.v2</h2> |
|
|
<p> |
|
|
98 verses × 18 speakers ≈ 2 h, with deliberate errors and human annotations. |
|
|
<code>load_dataset("IqraEval/Iqra_QuranMB_v2")</code> |
|
|
</p> |
|
|
|
|
|
<h2>Resources & Links</h2> |
|
|
<ul> |
|
|
<li><a href="https://colab.research.google.com/drive/1kUVsgEzhrB1ujr85SArNoUcKJh-jHdza?usp=sharing" target="_blank">Try Our Models on Google Colab</a></li> |
|
|
<li><a href="https://github.com/Iqra-Eval/MSA_phonetiser" target="_blank">Phonetiser script (GitHub)</a></li> |
|
|
<li><a href="https://huggingface.co/datasets/IqraEval/Iqra_train" target="_blank">Training & Dev Data (Hugging Face)</a></li> |
|
|
<li><a href="https://huggingface.co/datasets/IqraEval/Iqra_TTS" target="_blank">TTS Data (Hugging Face)</a></li> |
|
|
<li><a href="https://github.com/Iqra-Eval/interspeech_IqraEval" target="_blank">Baseline Systems & Scripts (GitHub)</a></li> |
|
|
</ul> |
|
|
|
|
|
<h2>Submission Details (Draft)</h2> |
|
|
<p> |
|
|
Submit a UTF-8 CSV named <code>teamID_submission.csv</code> with two columns: |
|
|
</p> |
|
|
<ul> |
|
|
<li><strong>ID:</strong> audio filename (no extension)</li> |
|
|
<li><strong>Labels:</strong> predicted phoneme sequence (space-separated)</li> |
|
|
</ul> |
|
|
<pre> |
|
|
ID,Labels |
|
|
0000_0001, i n n a m a a y a … |
|
|
0000_0002, m a a n a n s a … |
|
|
… |
|
|
</pre> |
|
|
<p> |
|
|
<strong>Note:</strong> no extra spaces, single CSV, no archives. |
|
|
</p> |
|
|
|
|
|
<h2>Evaluation Criteria</h2> |
|
|
<p> |
|
|
IqraEval Leaderboard is based on phoneme-level <strong>F1-score</strong>. |
|
|
We use a hierarchical evaluation (detection + diagnostic) per <a href="https://arxiv.org/pdf/2310.13974" target="_blank">MDD Overview</a>. |
|
|
</p> |
|
|
<ul> |
|
|
<li><em><strong>What is said</strong></em>: annotated phoneme sequence</li> |
|
|
<li><em><strong>What is predicted</strong></em>: model output</li> |
|
|
<li><em><strong>What should have been said</strong></em>: reference sequence</li> |
|
|
</ul> |
|
|
<p>From these we compute:</p> |
|
|
<ul> |
|
|
<li><strong>TA:</strong> correct phonemes accepted</li> |
|
|
<li><strong>TR:</strong> mispronunciations correctly detected</li> |
|
|
<li><strong>FR:</strong> correct phonemes flagged as errors</li> |
|
|
<li><strong>FA:</strong> mispronunciations missed</li> |
|
|
</ul> |
|
|
<p>Rates:</p> |
|
|
<ul> |
|
|
<li><strong>FRR:</strong> FR/(TA+FR)</li> |
|
|
<li><strong>FAR:</strong> FA/(FA+TR)</li> |
|
|
<li><strong>DER:</strong> DE/(CD+DE)</li> |
|
|
</ul> |
|
|
<p> |
|
|
Plus standard Precision, Recall, F1 for detection: |
|
|
<ul> |
|
|
<li>Precision = TR/(TR+FR)</li> |
|
|
<li>Recall = TR/(TR+FA)</li> |
|
|
<li>F1 = 2·P·R/(P+R)</li> |
|
|
</ul> |
|
|
</p> |
|
|
|
|
|
<h2>Suggested Research Directions</h2> |
|
|
<ol> |
|
|
<li> |
|
|
<strong>Advanced Mispronunciation Detection Models</strong><br> |
|
|
Apply state-of-the-art self-supervised models (e.g., Wav2Vec2.0, HuBERT), using variants that are pre-trained/fine-tuned on Arabic speech. These models can then be fine-tuned on Quranic recitations to improve phoneme-level accuracy. |
|
|
</li> |
|
|
<li> |
|
|
<strong>Data Augmentation Strategies</strong><br> |
|
|
Create synthetic mispronunciation examples using pipelines like |
|
|
<a href="https://arxiv.org/abs/2211.00923" target="_blank">SpeechBlender</a>. |
|
|
Augmenting limited Arabic/Quranic speech data helps mitigate data scarcity and improves model robustness. |
|
|
</li> |
|
|
<li> |
|
|
<strong>Analysis of Common Mispronunciation Patterns</strong><br> |
|
|
Perform statistical analysis on the QuranMB dataset to identify prevalent errors (e.g., substituting similar phonemes, swapping vowels). |
|
|
These insights can drive targeted training and tailored feedback rules. |
|
|
</li> |
|
|
</ol> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<h2>Registration</h2> |
|
|
<p> |
|
|
Teams and individual participants must register to gain access to the test set. Please complete the registration form using the link below: |
|
|
</p> |
|
|
<p> |
|
|
<a href="https://docs.google.com/forms/d/e/1FAIpQLSf8qVKV1C9JVY7gUloQRLX8iMBUaZNFtYHBcqG6obJU0JauGw/viewform" target="_blank">Registration Form</a> |
|
|
</p> |
|
|
<p> |
|
|
Registration opens on June 10, 2025. |
|
|
</p> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<h2>Future Updates</h2> |
|
|
<p> |
|
|
Further details on the open-set leaderboard submission will be posted on the shared task website (June 20, 2025). Stay tuned! |
|
|
</p> |
|
|
|
|
|
|
|
|
<h2>Contact and Support</h2> |
|
|
<p> |
|
|
For inquiries and support, reach out to the task coordinators at |
|
|
<a href="mailto:iqraeval@googlegroups.com">iqraeval@googlegroups.com</a>. |
|
|
</p> |
|
|
|
|
|
<h2>References</h2> |
|
|
<ul> |
|
|
<li>El Kheir Y. et al., “SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation,” arXiv:2211.00923, 2022.</li> |
|
|
<li>Al Harere A. & Al Jallad K., “Mispronunciation Detection of Basic Quranic Recitation Rules using Deep Learning,” arXiv:2305.06429, 2023.</li> |
|
|
<li>Aly S. A. et al., “ASMDD: Arabic Speech Mispronunciation Detection Dataset,” arXiv:2111.01136, 2021.</li> |
|
|
<li>Moustafa A. & Aly S. A., “Efficient Voice Identification Using Wav2Vec2.0 and HuBERT…,” arXiv:2111.06331, 2021.</li> |
|
|
<li>El Kheir Y. et al., “Automatic Pronunciation Assessment – A Review,” arXiv:2310.13974, 2021.</li> |
|
|
</ul> |
|
|
</div> |
|
|
</body> |
|
|
</html> |
|
|
|
|
|
|
