Speech visualization simulation research for deaf-mute

Deaf-mutes have the stronger advantage of visual identification ability and visual memory ability for color, a new speech visualization method for deaf-mute was proposed,it created readable patterns by integrating different speech features into a single picture. Firstly, series preprocessing of speech signals were done. Secondly, extracting features were done, among them, using three formant features mapped principal color information, using the length of pronunciation mapped width information, using harmonic intensity mapped length information, and then all features used as the inputs of neural network, the outputs of neural network mapped the texture information. We evaluated the visualized speech in a preliminary test, the test result shows that the method has very good robustness, the correct answer rate reaches 94.56% of vowel and consonant, 85.75% of two-bopomofo and 78.05% of three-bopomofo.