METHODS OF ENCODING SPEECH SEGMENTS AND HEIGHT CONTROL FOR SPEECH SYNTHESIS SYSTEMS.

摘要

The present invention refers to a technology relating to a speech synthesis system, and uses a method of periodic waveform decomposition and repositioning which is a coding method in which signals of a voiced sound interval in the original speech is broken down into wavelets, each of which corresponds to a speech waveform for a period created by each glottal impulse, and the wavelets are respectively coded and stored, a technology by which the wavelets closest to the positions to be positioned the wavelets are chosen from memorized wavelets, then decoded and superimposed on each other so that the quality of the original sound can be preserved and the duration and pitch frequency of the speech segment can be controlled at will.