Discriminative of wavelet sub-signals for speech recognition

In this paper, we propose a method for decomposing speech signals, evaluating the discriminative, and determining the representative vectors of signal sets. At first, we decompose all speech signals with the level four Db4 wavelet decomposition to reconstruct the approximation sub-signals of all four levels, transfer all the speech signals and the sub-signals into the Linear Prediction Codes (LPC), and calculate the Difference vectors between the LPC (DLPC) of the speech signals and that of the approximation sub-signals of different levels. We adopt those LPC and DLPC vectors as the feature vectors, evaluate the discriminative of each set of feature vectors, and adopt the mean vectors of the clusters as the representative vectors. We can use those to set the parameters of the speech recognizer. Although the experimental results are only valid for the speech signals and the wavelet functions used for this experimental study, it should provide valuable references in general applications.