Related papers: Fanar 2.0: Arabic Generative AI Stack

Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European…

Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first…

Conventional methods for aggregating layers in fine-tuned self-supervised speech models, such as using the final layer or weighted sum, suffer from information bottlenecks and static feature weighting for all dataset examples. We propose…

Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present…

We explore the performance of several state-of-the-art automatic speech recognition (ASR) models on a large-scale Arabic speech dataset, the SADA (Saudi Audio Dataset for Arabic), which contains 668 hours of high-quality audio from Saudi…

Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored…

We propose a novel framework, termed Fourier-Activated Adapter (FAA), for parameter-efficient fine-tuning of large pre-trained language models. By incorporating random Fourier features into lightweight adapter modules, FAA decomposes…

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…

Recently, Retrieval Augmented Generation (RAG) has emerged as a powerful technique in natural language processing, combining the strengths of retrieval-based and generation-based models to enhance text generation tasks. However, the…

Arabic language is one of the most widely spoken languages. This language has a complex morphological structure and is considered as one of the most prolific languages in terms of article linguistic. Therefore, Arabic Information Retrieval…

Code-switching -- the natural alternation between two languages within a single utterance -- remains one of the most challenging and under-studied conditions for automatic speech recognition (ASR). We present a benchmark evaluating five…

Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from…

We present our effort to create a large Multi-Layered representational repository of Linguistic Code-Switched Arabic data. The process involves developing clear annotation standards and Guidelines, streamlining the annotation process, and…

One of the key tasks in machine learning for tabular data is feature engineering. Although it is vital for improving the performance of models, it demands considerable human expertise and deep domain knowledge, making it labor-intensive…

Current Adaptive Bit Rate (ABR) methods react to network congestion after it occurs, causing application layer buffering and latency spikes in live video streaming. We introduce a proactive semantic control channel that enables coordination…

This paper presents the first comprehensive comparative analysis of modern machine learning architectures for transliteration between Tajik (Cyrillic script) and Persian (Arabic script). A key contribution is the creation and validation of…

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range…

Developing accurate biomedical Question Answering (QA) systems in low-resource languages remains a major challenge, limiting equitable access to reliable medical knowledge. This paper introduces BanglaMedQA and BanglaMMedBench, the first…

Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this…

We present Gazal-R1, a 32-billion-parameter language model that achieves state-of-the-art performance in medical reasoning while providing transparent, step-by-step explanations for clinical decision-making. Built upon Qwen3 32B, our model…