Speaker Verification Using Hybrid Scheme for Arabic Speech

In this work , a hybrid scheme for Arabic speech for the recognition of the speaker verification is presented . The schemc is hybrid as utilizes the traditional digital signal processing and neural network . Kohoncn neural network has been used as a recognizer for speaker verification after extract spectral features from an acoustic signal by Fast Fourier Transformation Algorithm(FFT) . The system was implemented using a PENTIUM processor , 1000 MHZ compatible and MS-dos 6.2