14 citations · 46 across the 26 of their papers we have counts for
33 papers
AraYoungVoices: A Diverse L1/L2 Corpus of Arabic Child and Adolescent Speech
Shammur Absar Chowdhury, Zien Sheikh Ali, Houssam Eddine-Othman Lachemat +1
State-of-the-art ASR systems primarily target native adult speech, leading to substantial performance gaps for children, adolescents, and L2 speakers. We introduce AraYoungVoices,…
Child ASR Adaptation with Adult Retention: An Empirical Study
Houssam Eddine-Othman Lachemat, Shammur Absar Chowdhury
Automatic Speech Recognition (ASR) systems often underperform for children and non-native speakers, while adapting adult ASR models to child speech can cause adult-speech forgettin…
Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal
Syeda Faiza Ahmed Sara, Shammur Absar Chowdhury
Training automated pronunciation assessment often relies on labeled learner errors or non-native corpora that are costly to collect. We propose a lightweight framework trained only…
WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
Zien Sheikh Ali, Hamdy Mubarak, Soon-Gyo Jung +3
Large Language Models (LLMs) voice assistants are commonly built as cascaded Automatic Speech recognition (ASR) to LLM systems, where recognition errors can distort user intent. Di…
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
Firoj Alam, Shammur Absar Chowdhury, Enamul Hoque Prince
Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and compute-heavy. The tutorial offe…
IQRA 2026: Interspeech Challenge on Automatic Pronunciation Assessment for Modern Standard Arabic (MSA)
Yassine El Kheir, Amit Meghanani, Mostafa Shahin +5
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…
HARNESS: Lightweight Distilled Arabic Speech Foundation Models
Vrunda N. Sukhadia, Shammur Absar Chowdhury
Large self-supervised speech (SSL) models achieve strong downstream performance, but their size limits deployment in resource-constrained settings. We present HArnESS, an Arabic-ce…
Fanar 2.0: Arabic Generative AI Stack
FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad +34
We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to…
HARNESS: Lightweight Distilled Arabic Speech Foundation Models
Vrunda N. sukhadia, Shammur Absar Chowdhury
Large pre-trained speech models excel in downstream tasks but their deployment is impractical for resource-limited environments. In this paper, we introduce HArnESS, the first Arab…
Fanar: An Arabic-Centric Multimodal Generative AI Platform
Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad +39
We present Fanar, a platform for Arabic-centric multimodal generative AI systems, that supports language, speech and image generation tasks. At the heart of Fanar are Fanar Star an…
GenAI Content Detection Task 2: AI vs. Human -- Academic Essay Authenticity Challenge
Shammur Absar Chowdhury, Hind Almerekhi, Mucahid Kutlu +5
This paper presents a comprehensive overview of the first edition of the Academic Essay Authenticity Challenge, organized as part of the GenAI Content Detection shared tasks colloc…
CAFE A Novel Code switching Dataset for Algerian Dialect French and English
Houssam Eddine-Othman Lachemat, Akli Abbas, Nourredine Oukas +3
The paper introduces and publicly releases (Data download link available after acceptance) CAFE -- the first Code-switching dataset between Algerian dialect, French, and english la…
AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs
Basel Mousi, Nadir Durrani, Fatema Ahmad +6
Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introduci…
Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in Arabic
Yassine El Kheir, Hamdy Mubarak, Ahmed Ali +1
This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich…
NativQA: Multilingual Culturally-Aligned Natural Query for LLMs
Md. Arid Hasan, Maram Hasanain, Fatema Ahmad +6
Natural Question Answering (QA) datasets play a crucial role in evaluating the capabilities of large language models (LLMs), ensuring their effectiveness in real-world applications…
Children's Speech Recognition through Discrete Token Enhancement
Vrunda N. Sukhadia, Shammur Absar Chowdhury
Children's speech recognition is considered a low-resource task mainly due to the lack of publicly available data. There are several reasons for such data scarcity, including expen…
Speech Representation Analysis based on Inter- and Intra-Model Similarities
Yassine El Kheir, Ahmed Ali, Shammur Absar Chowdhury
Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of…
Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognition
Rabindra Nath Nandi, Mehadi Hasan Menon, Tareq Al Muntasir +5
One of the major challenges for developing automatic speech recognition (ASR) for low-resource languages is the limited access to labeled data with domain-specific variations. In t…
Automatic Pronunciation Assessment -- A Review
Yassine El Kheir, Ahmed Ali, Shammur Absar Chowdhury
Pronunciation assessment and its application in computer-aided pronunciation training (CAPT) have seen impressive progress in recent years. With the rapid growth in language proces…
Speech collage: code-switched audio generation by collaging monolingual corpora
Amir Hussein, Dorsa Zeinali, Ondřej Klejch +6
Designing effective automatic speech recognition (ASR) systems for Code-Switching (CS) often depends on the availability of the transcribed CS resources. To address data scarcity,…
The complementary roles of non-verbal cues for Robust Pronunciation Assessment
Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali
Research on pronunciation assessment systems focuses on utilizing phonetic and phonological aspects of non-native (L2) speech, often neglecting the rich layer of information hidden…
LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
Fahim Dalvi, Maram Hasanain, Sabri Boughorbel +10
The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several…
MyVoice: Arabic Speech Resource Collaboration Platform
Yousseif Elshahawy, Yassine El Kheir, Shammur Absar Chowdhury +1
We introduce MyVoice, a crowdsourcing platform designed to collect Arabic speech to enhance dialectal speech technologies. This platform offers an opportunity to design large diale…
Multi-View Multi-Task Representation Learning for Mispronunciation Detection
Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali
The disparity in phonology between learner's native (L1) and target (L2) language poses a significant challenge for mispronunciation detection and diagnosis (MDD) systems. This cha…