A talking robot and the interactive speech training for hearing‐impaired.

A speech trainer employing a talking robot for auditory-impaired people will be introduced. The talking robot consists of mechanically-designed vocal organs such as a vocal tract, a nasal cavity, artificial vocal cords, and a sound analyzer with a microphone system, and the mechanical parts are fully controlled by ten servomotors for generating humanlike voices. The robot autonomously learns the relation between motor control parameters and the generated vocal sounds by an auditory feedback control, in which a Self-organizing neural network is employed for the adaptive learning. By employing the robot and its properties, the authors have constructed an interactive speech training system. The training is divided into two approaches; one is to use the robot for showing the shape and the motion of the vocal organs, and the other is to use a topological map for presenting the difference of phonetic features of a traine’s voices. While referring to the robot motions and the phonetic characteristics, a trainee is able to interactively practice vocalization for acquiring clear speech with appropriate speech articulations. To assess the validity of the training system, a practical experiment was conducted by 19 subjects in a school for the deaf children. The talking robot is expected to intensively teach auditory-impaired patients the clear speech articulations.