Towards using CMU Sphinx Tools for the Holy Quran recitation verification

The use of the Automatic Speech Recognition (ASR) technology is being used is many different applications that help simplify the interaction with a wider range of devices. This paper investigates the use of a simplified set of phonemes in an ASR system applied to Holy Quran. The Carnegie Mellon University Sphinx 4 tools were used to train and evaluate an acoustic model on Holy Quran recitations that are widely available online. The building of the acoustic model was done using a simplified list of phonemes instead of the mainly used Romanized in order to simplify the process of training the acoustic model. In this paper, the experiment resulted in Word Error Rates (WER) as low as 1.5% even with a very small set of audio files to use in the training phase