@inproceedings{mohamed-hedeya-2026-real,
title = "Real-Time {Q}uranic Recitation Assessment on Mobile Devices Using Streaming Inference and Model Compression",
author = "Mohamed, Abdelrahman Ayman Amin and
Hedeya, Abdullah Haytham Mohamed Salah",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.30/",
pages = "433--443",
ISBN = "979-8-89176-473-6",
abstract = "Automatic Quranic recitation assessment requires accurate detection of phonetic and Tajweed-related pronunciation errors while providing low-latency feedback. However, most speech recognition models are designed for offline processing and are too large for deployment on consumer mobile devices.\par We present a real-time Quranic recitation assessment system based on a multi-head Wav2Vec2-BERT model trained to jointly predict phonemes and Tajweed Sifat attributes using Connectionist Temporal Classification. To enable streaming inference without retraining, we introduce an Adaptive Eager-Emission framework that combines heuristic output commitment, dynamic context expansion, and overlap recovery, reducing perceived latency while preserving long-range temporal features.\par For efficient on-device deployment, we propose a structured compression pipeline based on encoder pruning, recovery fine-tuning, and INT8 quantization with ONNX optimization, reducing a 600M-parameter, 2.4 GB model to a 24.5M-parameter, 36 MB model while maintaining recognition performance.\par The streaming framework consistently outperforms static sliding-window approaches across the accuracy{--}latency trade-off, achieving responsiveness as low as 1.0 s at roughly 2.1{\%} phoneme error rate (PER), or near-offline performance below 1{\%} PER at 6.0 s average chunk latency, while the production streaming configuration maintains 99.45{\%} average Sifat attribute accuracy. On a mid-range Android CPU, the compressed model runs at a real-time factor of 0.225 with a peak memory of about 600 MB."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-hedeya-2026-real">
<titleInfo>
<title>Real-Time Quranic Recitation Assessment on Mobile Devices Using Streaming Inference and Model Compression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="given">Ayman</namePart>
<namePart type="given">Amin</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">Haytham</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="given">Salah</namePart>
<namePart type="family">Hedeya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Automatic Quranic recitation assessment requires accurate detection of phonetic and Tajweed-related pronunciation errors while providing low-latency feedback. However, most speech recognition models are designed for offline processing and are too large for deployment on consumer mobile devices.\par We present a real-time Quranic recitation assessment system based on a multi-head Wav2Vec2-BERT model trained to jointly predict phonemes and Tajweed Sifat attributes using Connectionist Temporal Classification. To enable streaming inference without retraining, we introduce an Adaptive Eager-Emission framework that combines heuristic output commitment, dynamic context expansion, and overlap recovery, reducing perceived latency while preserving long-range temporal features.\par For efficient on-device deployment, we propose a structured compression pipeline based on encoder pruning, recovery fine-tuning, and INT8 quantization with ONNX optimization, reducing a 600M-parameter, 2.4 GB model to a 24.5M-parameter, 36 MB model while maintaining recognition performance.\par The streaming framework consistently outperforms static sliding-window approaches across the accuracy–latency trade-off, achieving responsiveness as low as 1.0 s at roughly 2.1% phoneme error rate (PER), or near-offline performance below 1% PER at 6.0 s average chunk latency, while the production streaming configuration maintains 99.45% average Sifat attribute accuracy. On a mid-range Android CPU, the compressed model runs at a real-time factor of 0.225 with a peak memory of about 600 MB.</abstract>
<identifier type="citekey">mohamed-hedeya-2026-real</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>433</start>
<end>443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Real-Time Quranic Recitation Assessment on Mobile Devices Using Streaming Inference and Model Compression
%A Mohamed, Abdelrahman Ayman Amin
%A Hedeya, Abdullah Haytham Mohamed Salah
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F mohamed-hedeya-2026-real
%X Automatic Quranic recitation assessment requires accurate detection of phonetic and Tajweed-related pronunciation errors while providing low-latency feedback. However, most speech recognition models are designed for offline processing and are too large for deployment on consumer mobile devices.\par We present a real-time Quranic recitation assessment system based on a multi-head Wav2Vec2-BERT model trained to jointly predict phonemes and Tajweed Sifat attributes using Connectionist Temporal Classification. To enable streaming inference without retraining, we introduce an Adaptive Eager-Emission framework that combines heuristic output commitment, dynamic context expansion, and overlap recovery, reducing perceived latency while preserving long-range temporal features.\par For efficient on-device deployment, we propose a structured compression pipeline based on encoder pruning, recovery fine-tuning, and INT8 quantization with ONNX optimization, reducing a 600M-parameter, 2.4 GB model to a 24.5M-parameter, 36 MB model while maintaining recognition performance.\par The streaming framework consistently outperforms static sliding-window approaches across the accuracy–latency trade-off, achieving responsiveness as low as 1.0 s at roughly 2.1% phoneme error rate (PER), or near-offline performance below 1% PER at 6.0 s average chunk latency, while the production streaming configuration maintains 99.45% average Sifat attribute accuracy. On a mid-range Android CPU, the compressed model runs at a real-time factor of 0.225 with a peak memory of about 600 MB.
%U https://aclanthology.org/2026.arabicnlp-main.30/
%P 433-443
Markdown (Informal)
[Real-Time Quranic Recitation Assessment on Mobile Devices Using Streaming Inference and Model Compression](https://aclanthology.org/2026.arabicnlp-main.30/) (Mohamed & Hedeya, ArabicNLP 2026)
ACL