Speech Visualization based on Robust Self-organizing Map (RSOM) for the Hearing Impaired

This paper describes a novel speech visualization method that creates a readable pattern based on robust self-organizing map (RSOM). According to SOM, RSOM introduces a time enhanced mechanism to improve system performance. The method remedies the defect that SOM only provides spatial topographic map ignoring temporal factor which is extremely important for speech signal. Firstly, speech signal undergoes a series of preprocessing course. Secondly, we make use of RSOM decreasing the dimension of speech feature vector. Finally, we utilize plot display algorithm to generate a speech plot. The speech feature after dimension decreasing by RSOM 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.