作者: Jalal Karam
DOI:
关键词: Pattern recognition 、 Artificial neural network 、 Wavelet packet decomposition 、 Fourier transform 、 Biorthogonal system 、 Artificial intelligence 、 Mel scale 、 Speech recognition 、 Arabic numerals 、 Mathematics 、 Wavelet 、 Radial basis function
摘要: In this paper, a Neural Network (NN) approach for the recognition of Arabic digits is presented. The two phases training and testing in Radial Basis Functions (RBF) type network described. Biorthogonal Wavelets are constructed used analysis generated subwords digits. This decomposes spoken based on acoustical information contained within speech signals. procedure locates boundaries between by finding peaks function representing spectral changes consecutive frames. Frame-based energy parameters derived from Wavelet Packet Scale (WPS) deriving Spectral Variation Function (SVF). Three wavelets as analyzing functions their performances compared with that Orthogonal counterpart traditional Fourier Mel scale approach.