Biorthoganal wavelet packets and Mel scale analysis for automatic recognition of Arabic speech via radial basis functions

作者: Jalal Karam

DOI:

关键词: Pattern recognitionArtificial neural networkWavelet packet decompositionFourier transformBiorthogonal systemArtificial intelligenceMel scaleSpeech recognitionArabic numeralsMathematicsWaveletRadial 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.

参考文章(23)
Jalal Karam, Radial basis functions with wavelet packets for recognizing Arabic speech international conference on circuits systems electronics control signal processing. pp. 34- 39 ,(2010)
Jalal Karam, A new approach in wavelet based speech compression international conference on mathematical methods computational techniques and intelligent systems. pp. 228- 233 ,(2008)
A. Drygajlo, New fast wavelet packet transform algorithms for frame synchronized speech processing international conference on spoken language processing. ,vol. 1, pp. 410- 413 ,(1996) , 10.1109/ICSLP.1996.607141
L. R. Rabiner, M. R. Sambur, An Algorithm for Determining the Endpoints of Isolated Utterances Bell System Technical Journal. ,vol. 54, pp. 297- 315 ,(1975) , 10.1002/J.1538-7305.1975.TB02840.X
R. KRONLAND-MARTINET, J. MORLET, A. GROSSMANN, ANALYSIS OF SOUND PATTERNS THROUGH WAVELET TRANSFORMS International Journal of Pattern Recognition and Artificial Intelligence. ,vol. 01, pp. 273- 302 ,(1987) , 10.1142/S0218001487000205
J. Wilpon, L. Rabiner, A modified K-means clustering algorithm for use in isolated work recognition IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 33, pp. 587- 594 ,(1985) , 10.1109/TASSP.1985.1164581
Richard Kronland-Martinet, The Wavelet Transform for Analysis, Synthesis, and Processing of Speech and Music Sounds Computer Music Journal. ,vol. 12, pp. 11- ,(1988) , 10.2307/3680149
Ingrid Daubechies, Ten Lectures on Wavelets ,(1992)
Lawrence R. Rabiner, Ronald W. Schafer, Digital Processing of Speech Signals ,(1978)