Continuous Arabic Speech Segmentation using FFT Spectrogram

This paper describes a phoneme segmentation algorithm that uses fast Fourier transform (FFT) spectrogram. The algorithm has been implemented and tested for utterances of continuous Arabic speech of 10 male speakers that contain almost 2346 phonemes in total. The recognition system determines the phoneme boundaries and identifies them as pauses, vowels and consonants. The system uses intensity and phoneme duration for separating pauses from consonants. Intensity in particular is used to detect two specific consonants (/r/, /hf) when they are not detected through the spectrographic information. Segmentation accuracy of 95.39% for the overall system has been achieved