A system for teaching speech to profoundly deaf children using synthesized acoustic and articulatory patterns

摘要

This paper describes a computer assisted method of teaching profoundly deaf children to speak, which employs the unique feature of an integrated text-to-speech system (TTS). Our earlier speech training system presented a series of speech parameters, derived from articulatory instruments and acoustic analysis, in a visual form. In that system, teacher's speech is input to the system and used as a model for the children to follow, and the children's speech is monitored to provide feedback. As with other computer-aided speech training systems (e.g. [2]), the teacher-assisted trainer is limited by the time students have with speech teachers. Several computer-based systems for providing information as to the desired acoustic and articulatory patterns and feedback showing what the children are doing already exist. In our system, we have developed an articulatory component which synthesizes tongue-palate contact patterns for the children to follow.