<![CDATA[Hijaiyah letter is the letter of constituent words in the Quran. Hijaiyah letter consists of 28 letters, with the letters symbolize consonant to vowel sounds while denoted by harokat / punctuation. Hijaiyah letter is part of the Arabic language that has characteristics both in writing and speech. Speech recognition system or voice recognition system is a system used to process voice signals into data that can be recognized by the computer [1]. To be able to do the voice recognition feature extraction methods are needed (feature extraction) and classifier. Sound signal that has been extracted character then generate information that can be analyzed for each variation existing voice signal. Of the characteristics that exist in each phoneme try to recognize it and convert it into text [2]. Methods of extraction of the characteristics used in this final project is Linear Predicitive Coding (LPC), then the feature generated from LPC quantized of each vector using the K-Means Clustering and for the classifier used when training and testing is the method of Hidden Markov Model (HMM). After several test scenarios obtained the best accuracy for testing is 58.93% and training is 99.60% with data 28 class.]]>
Copyrights © 2016
