Novel approaches to Arabic speech recognition: report from

Although Arabic is currently one of the most widely spoken lan-guages in the world, there has been relatively little speech recog-nition research on Arabic compared to other languages. Moreover, most previous work has concentrated on the recognition of for-mal rather than dialectal Arabic. This paper reports on our project at the 2002 Johns Hopkins Summer Workshop, which focused on the recognition of dialectal Arabic. Three problems were ad-dressed: (a) the lack of short vowels and other pronunciation infor-mation in Arabic texts; (b) the morphological complexity of Ara-bic; and (c) the discrepancies between dialectal and formal Ara-bic. We present novel approaches to automatic vowel restoration, morphology-based language modeling and the integration of out-of-corpus language model data, and report significant word error rate improvements on the LDC Arabic CallHome task