Application of Wavelet Transform for Speech Signal Segmentation
В. М. Смирнов, V. N. Filatov · 2019 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) · 2019
The article discusses the possibility of using the wavelet transform for speech signal segmentation. To identify the attributes of phonemes it is proposed to use the Daubechies multiscale wavelet transform. Taking into account the characteristics of the speech signal frequency range, the required number of levels of decomposition is selected. The proposed speech signal processing algorithm and the results of the segmentation program for chosen significant characteristic words are given in Matlab environment.