Speaker Dependent Voice Recognition Using Discrete Wavelet Transform

This paper presents effective and robust method for the extracting of features in the speaker dependent voice recognition. Based on the time-frequency multi-resolution property of wavelet transform, the input speech signal is decomposed into various frequency channels. The major issues concerning the design in this paper for wavelet based speaker voice recognition system are choosing the optimal wavelets for the speech signals, decomposition level in the discrete wavelet transform, and selecting the feature vectors from the wavelet coefficients. And finally, the wavelet-based voice recognition system and its performance are discussed and highlighted.