Modeling and automating detection of errors in Arabic language learner speech

Human tutors, in dealing with non-native speakers, draw from their knowledge of common learner mistakes to understand learner speech and offer effective corrective advice. In this paper we present our work towards embedding some of this knowledge in the speech recognition and learner speech error detection subsystems of the Tactical Language Training System (TLTS). We discuss the implementation and effectiveness of our methodology which uses a combination of rule based and probabilistic models derived from linguistic knowledge about the target language and annotated speech to identify potential learner errors, detect them using ASR and to provide the user with corrective feedback based on error severity and factors such as the learner history. Evaluation results show that our system can provide effective feedback to the learner with good accuracy.