الفهرس Only 14 pages are availabe for public view
 |  | from | 109 |  |  |
| | | from | 109 | | |
Abstract
With the prevalence of the Computer Aided Pronunciation Learning (CAPL) applications, an accurate automatic pronunciation verification method is needed to automate the learning process without affecting the learning quality. In this thesis we propose a phoneme-level pronunciation verification method for Quranic Arabic based on anti-phone model. For each phoneme a binary support vector machine (SVM) classifier is trained to discriminate each phoneme from other phonemes. The classifier is trained using speech attribute features derived from a bank of speech attribute detectors, namely manners and places of articulation.The feedforward deep neural network (DNN) architecture is utilized for the speech attribute detectors. The system is evaluated against speech corpora collected from fluent Quran reciters and achieved phoneme-level false-acceptance and false-rejection rates ranging from 2% to 25%