Speech Denoising and Syllable Segmentation Based on Fractal Dimension

摘要

In order to enhance the effect of existing wavelet denoising and determine beginning-ending points of each syllable in continuous speech, the thesis improves algorithms based on fractal theory. Firstly, the algorithm use dynamic threshold algorithm which combines fractal dimension with wavelet transform to denoise the speech signal; on this basis, the paper design an algorithm which is based on fractal dimension trajectory to carry out syllable segmentation. The experimental results show that the improved algorithms not only betterly carry out speech denoising and syllable segmentation, but also have good robustness. In the case of low SNR,the algorithm is still able to maintain high accuracy rate.