The research and implementation of Mongolian text to speech system

Abstract

In this paper, a Mongolian text to speech system using the PSOLA method is presented. According to the characteristics of Mongolian, the system uses a speech waveform concatenation method that is comparatively mature in text-to-speech synthesis. The author also set up a usable Mongolian diphone database, and the elements of the database are all marked accurately. At the same time, a speech synthesis dictionary is firstly set up. The experiment of prosodic modifications is also done and the result is comparatively satisfying. Mongolian is an influential language in the world, so our system will surely improve the Mongolian information processing.