Automatic assessment of spoken modern standard Arabic

Abstract

Proficiency testing is an important ingredient in successful language teaching. However, repeated testing for course placement, over the course of instruction or for certification can be time-consuming and costly. We present the design and validation of the Versant Arabic Test, a fully automated test of spoken Modern Standard Arabic, that evaluates test-takers' facility in listening and speaking. Experimental data shows the test to be highly reliable (test-retest r=0.97) and to strongly predict performance on the ILR OPI (r=0.87), a standard interview test that assesses oral proficiency.