Study of Sound Clarity Method for Body Conducted Speech using Linear Predictive in Sub-word, and Sound Quality Evaluation by means of Articulatory Feature Analysis

Abstract

Japan is presently aging more rapidly than anywhere else in the world. Concurrently, the number of patients suffering speech disorders is increasing every year, and the incidence is higher as age increases. Those suffering from speech disordered face problems with communicating in daily conversation. They are often able to communicate with speech substitutes, but these typically do not provide a sufficient sound frequency range to be understood in conversation. Therefore, we proposed a speech support system using body-conducted speech recognition. This system retrieves speech from body-conducted sound via a transfer function, using recognition to select a sub-word sequence and its duration. In this study, we demonstrate the effectiveness of producing clear body-conducted speech using a linear predictive coefficient instead of a transfer function. We estimated interval information by heuristic method to divide body-conducted speech into syllables as in past study. In this study, we used continuous sub-word recognition automatically. To confirm the improvement in synthesized speech, a jury test and articulatory feature analysis were employed.