Feature extraction of some Quranic recitation using Mel-Frequency Cepstral Coeficients (MFCC)

This report describes the work done for training and testing Arabic speech recognition system using the KALDI toolkit. Each person's voice is different. Thus, the Holy Quran sound, which had been recited by most of reciters will probably tend to differ a lot from one person to another. Although those Quranic sentences were particularly taken from the same verse, but the way of the sentence in The Holy Quran been recited or delivered may be different. It may produce the contrast sounds for the different reciters. Those same combinations of letters maybe pronounced differently due to the use of diacritics. This paper explores the viability of Mel-Frequency Cepstral Coefficient (MFCC) technique to extract features from Quranic verse recitation. Features extraction is important to prepare data for classification process. MFCC is one of the most popular feature extraction techniques used in speech recognition, whereby it is based on the frequency domain of Mel scale for human ear scale. MFCCs consist of preprocessing, framing, windowing, DFT, Mel Filterbank, Logarithm and Discrete Cosine Transform DCT.