Comparative Analysis of Various Transformation Techniques for Voiceless Consonants Modeling

In this paper, a comparison of various transformation techniques, namely Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT) and Discrete Walsh Hadamard Transform (DWHT) are performed in the context of their application to voiceless consonant modeling. Speech features based on these transformation techniques are extracted. These features are mean and derivative values of cepstrum coefficients, derived from each transformation. Feature extraction is performed on the speech signal divided into short-time segments. The kNN and Naive Bayes methods are used for phoneme classification. We consider both classification accuracies and computational time. Experiments show that DFT and DCT give better classification accuracy than DWHT. The result of DFT was not significantly different from DCT, but it was for DWHT. The same tendency was revealed for DCT. It was checked with the usage of the ANOVA test that the difference between results obtained by DCT and DWHT is significant.