Speech Production Model and its Application to Speech Synthesis System - Speech Synthesis by Mimicing Human Speech Production -

Speech is produced by articulating speech organs such as the jaw, tongue, and lips. We have developed an articulatory-based speech synthesis model that converts a phoneme string into a continuous acoustic signal by mimicing the human speech production process. This paper describes a computational model of the speech production process which involves a motor process to generate articulatory movements from the motor task sequence and articulatory-to-acoustic mapping to determine the vocal-tract acoustic characteristics. † NTT Basic Research Laboratories.