A framework for pronunciation error detection and correction for non-native Arab speakers of English language

Abstract

This paper examines speakers’ systematic errors while speaking English as a foreign language (EFL) among students in Arab countries with the purpose of automatically recognizing and correcting mispronunciations using speech recognition, phonological features, and machine learning. Accordingly, three main steps are implemented towards this purpose: identifying the most frequently wrongly pronounced phonemes by Arab students, analyzing the systematic errors these students make in doing so, and developing a framework that can aid the detection and correction of these pronunciation errors. The proposed automatic detection and correction framework used the collected and labeled data to construct a customized acoustic model to identify and correct incorrect phonemes. Based on the trained data, the language model is then used to recognize the words. The final step includes construction samples of both correct and incorrect pronunciation in the phonemes model and then using machine learning to identify and correct the errors. The results showed that one of the main causes of such errors was the confusion that leads to wrongly utilizing a given sound in place of another. The automatic framework identified and corrected 98.2% of the errors committed by the students using a decision tree classifier. The decision tree classifier achieved the best recognition results compared to the five classifiers used for this purpose.