We present a new corpus of word-level listening errors collected from 62 native English speakers learning Arabic designed to inform models of spell checking for this learner population. While we use the corpus to assist in automated detection and correction of auditory errors in electronic dictionary lookup, the corpus can also be used as a phonological error layer, to be combined with a composition error layer in a more complex spell-checking system for non-native speakers. The corpus may be useful to instructors of Arabic as a second language, and researchers who study second language phonology and listening perception.

No abstract

No abstract

No abstract