A Hybrid Morphologically Decomposed Factored Language Models for Arabic LVCSR

Amr El-Desoky, Ralf Schlüter, Hermann Ney

Abstract: In this work, we try a hybrid methodology for language modeling where both morphological decomposition and factored language modeling (FLM) are exploited to deal with the complex morphology of Arabic language. At the end, we are able to obtain from 3.5% to 7.0% relative reduction in word error rate (WER) with respect to a traditional full-words system, and from 1.0% to 2.0% relative WER reduction with respect to a non-factored decomposed system.