Ahmed Rafea

Deep Learning Framework with Confused Sub-Set Resolution Architecture for Automatic Arabic Diacritization

2015 · IEEE/ACM Transactions on Audio Speech and Language Processing

The Arabic language belongs to a group of languages that require diacritization over their characters. Modern Standard Arabic (MSA) transcripts omit the diacritics, which are essential for many machine learning tasks like Text-To-Speech (TTS) systems. …