2 papers
cs.CL2026
More Data, Fewer Diacritics: Scaling Arabic TTS
Ahmed Musleh, Yifan Zhang, Kareem Darwish
Arabic Text-to-Speech (TTS) research has been hindered by the availability of both publicly available training data and accurate Arabic diacritization models. In this paper, we add…
cs.CL2025
BALSAM: A Platform for Benchmarking Arabic Large Language Models
Rawan Al-Matham, Kareem Darwish, Raghad Al-Rasheed +40
The impressive advancement of Large Language Models (LLMs) in English has not been matched across all languages. In particular, LLM performance in Arabic lags behind, due to data s…