Speech visualization based on wavelet transform for the hearing impaired

This paper describes a new speech visualization system that creates readable patterns by integrating combined feature into a single image. The system makes use of time-frequency analysis based on wavelet transform to simulate the band-pass filter property of basilar membrane. The method remedies the defect that Short Fourier Transform(SFT) has the same time-resolution and frequency resolution to different frequency ranges. The auditory feature is displayed on the CRT by plot patterns and the deaf can utilize their own brain to identify different speech for training their oral ability effectively. Firstly, speech signal undergoes a series of preprocessing course. Secondly, we make use of wavelet transform to process time-frequency analysis for speech signal and extract the feature value for speech visualization. Thirdly, we calculate that the feature value lies in which place in full array and obtain the combined feature value. Finally, we utilize plot display algorithm to generate a speech plot. The algorithm consists of three parts: coordinates partition, area computation and coordinates calculation of combined feature value.