An EfficientMispronunciation Detection System Using Discriminative Acoustic Phonetic Features for Arabic Consonants

Mispronunciation detection is an important component of Computer-Assisted Language Learning (CALL) systems.It helps students to learn new languages and focus on their individual pronunciation problems.In this paper, a novel discriminative Acoustic Phonetic Feature (APF) based technique is proposed to detect mispronunciations using artificial neural network classifier. By using domain knowledge, Arabic consonants arecategorizedinto two groups based on their acoustic similarities.The first group consists of consonants having similar ending sounds and the second group consists ofconsonants with completely different sounds. In our proposed technique, the discriminative acoustic features are required for classifier training. To extract these features, discriminativeparts of theArabic consonants are identified.As a test case, a dataset is collected from native/non-native, male/female and children of different ages. This dataset comprises of 5600 isolated Arabic consonants. The average accuracy of the system, when tested with simple acoustic features are found to be 73.57%.While the use of discriminative acoustic features has improved the average accuracy to 82.27%. Some consonant pairs that are acoustically very similar, produced poor results and termed as Bad Phonemes. A subjective analysis has also been carried out to verify the effectiveness of the proposed system.