Abstract:

Automatic articulation scoring makes the computer able to give feedback on the quality of pronunciation and eventually detect some phonemes miss-pronunciation. Computer-assisted language learning has evolved from simple interactive software that access the learner’s knowledge in grammar and vocabulary to more advanced systems that accept speech input as a result of the recent development of speech recognition. Therefore many computer based self teaching systems have been developed for several languages such English, Dutch and Chinese, however for Arabic; the research is still in its beginning. This study is part of the “Arabic Pronunciation improvement system for Malaysian Teachers of Arabic language” project which aimed at developing computer based systems for standards Arabic language instruction for Malaysian teachers of Arabic language. The system aims to help teachers to learn Arabic language quickly by focusing on the listening and speaking comprehension (receptive skills) to improve their pronunciation. In this paper we addressed the problem of giving marks for Arabic pronunciation by using a Automatic Speech Recognizer (ASR) based on Hidden Markov Models (HMM), thus our approach to pronunciation scoring is based on the HMM log-likelihood probability.

Keywords:

Arabic, pronunciation, recognition, correction, automatic speech recognizer.