The Qatar Computing Research Institute (QCRI) has released QASR, a 2,000-hour transcribed Arabic speech corpus collected from Aljazeera news broadcasts. The dataset features multi-dialect speech sampled at 16kHz, aligned with lightly supervised transcriptions and linguistically motivated segmentation. QCRI also released a 130M word dataset to improve language model training. Why it matters: QASR enables new research in Arabic speech recognition, dialect identification, punctuation restoration, and other NLP tasks for spoken data.
An MBZUAI team won the best paper award at the inaugural Arabic Natural Language Processing Conference for their work on processing Arabic speech. Their study establishes a new approach to tackle the complexities of spoken Arabic, which differs significantly from text-based language models. The team's approach aims to advance new tools for Arabic speakers by addressing challenges like intonation and the continuous nature of speech. Why it matters: This award highlights the importance of specialized research in Arabic NLP, as mainstream LLMs often face limitations in accurately processing the nuances of Arabic speech.
Egyptian AI startup Intella, specializing in Arabic speech recognition, has raised $12.5 million in funding. The round was led by বিনিয়োগ, with participation from other investors. Intella plans to use the capital to expand its Arabic AI speech models and related services. Why it matters: The funding will help advance Arabic language AI capabilities, which are currently underserved compared to English-centric models.
This paper benchmarks the performance of OpenAI's Whisper model on diverse Arabic speech recognition tasks, using publicly available data and novel dialect evaluation sets. The study explores zero-shot, few-shot, and full finetuning scenarios. Results indicate that while Whisper outperforms XLS-R models in zero-shot settings on standard datasets, its performance drops significantly when applied to unseen Arabic dialects.
MIT Technology Review reports on advancements in machine learning techniques that are significantly improving Arabic speech transcription capabilities. These developments aim to enhance the accuracy and robustness of Automatic Speech Recognition (ASR) systems for the complexities of the Arabic language, including its various dialects. The improvements are designed to overcome previous challenges in processing diverse phonetic patterns and linguistic nuances. Why it matters: This progress is vital for the development of more effective voice-enabled technologies, accessibility tools, and AI applications specifically tailored for Arabic-speaking populations in the Middle East and beyond.
This paper describes the MIT-QCRI team's Arabic Dialect Identification (ADI) system developed for the 2017 Multi-Genre Broadcast challenge (MGB-3). The system aims to distinguish between four major Arabic dialects and Modern Standard Arabic. The research explores Siamese neural network models and i-vector post-processing to handle dialect variability and domain mismatches, using both acoustic and linguistic features. Why it matters: The work contributes to the advancement of Arabic language processing, specifically in dialect identification, which is crucial for analyzing and understanding diverse Arabic speech content in media broadcasts.
MBZUAI highlighted five Emirati women making contributions in AI, entrepreneurship, and leadership, coinciding with Emirati Women’s Day. Fatima AlKhoori is pursuing a Ph.D. at MBZUAI, researching transformer models for autonomous vehicle traffic sign recognition using UAE and German datasets. Dr. Hanan Aldarmaki, an MBZUAI assistant professor, specializes in Arabic speech and language processing. Why it matters: Showcasing Emirati women in AI underscores the UAE's commitment to gender diversity and national talent development in advanced technology fields.
MBZUAI is highlighting five female leaders in AI for International Women’s Day, noting its 28% female student body. Dr. Farida Al Hosani is developing an AI healthcare solution for non-communicable diseases and was appointed VP of MBZUAI’s Alumni Advisory Board. Dr. Hanan Aldarmaki focuses on improving Arabic automated speech recognition and recently won an award for a paper on Arabic speech processing. Why it matters: Showcasing women in AI leadership helps promote diversity and inclusion in the field, especially in the context of the rapidly growing AI ecosystem in the UAE.