基于小波变换的语音信号可视化研究*

给出了一种新的语音信号的可视化方法，利用基于小波变换的时频分析方法来模拟基底膜带通滤波器的特性，克服了SFT（短时傅里叶变换）分析对高、低频段具有相同的时间分辨率和频率分辨率的缺点。对经过小波变换滤波后的语音信号进行特征编码形成语音的组合特征，将该组合特征作为一个新的特征量来表示语音信息，并将这种特征用简单的图形表示出来。利用聋哑人自身的大脑来识别语音，达到训练其口语的目的。

Speech visualization based on wavelet transform

This paper described a new speech visualization method that created readable patterns by integrating combined feature into a single image. The system made use of time-frequency analysis based on wavelet transform to simulate the band-pass filter property of basilar membrane. The method remedied the defect that short fourier transform(SFT) had the same time-resolution and frequency-resolution to different frequency ranges. The auditory feature was displayed on the CRT by plot patterns and the deaf could utilize their own brain to identify different speech for training their oral ability effectively. Firstly, speech signal underwent a series of preprocessing course. Secondly, made use of wavelet transform to process time-frequency analysis for speech signal and extracted the feature value for speech visualization. Then calculated that the feature value lay in which place in full array and obtained the combined feature value. Finally, utilized plot display algorithm to generate a speech plot.