A Method Of Speech Synthesis Based On Exciting VTFR In Chinese

It is difficult to synthesize the sonant in the speech synthesis especially in the synthesizing diphthong in speech synthesis. A kind of effective method for getting pitch period of voice is initiated in this paper. Adopt the exciting VTFR method to accomplish the speech synthesis of voice.At the same time, accomplishing the design of speech data base of Chinese names basically. Outline is as follows:(1) Preliminary study to the basic theory of speech synthesis. A kind of effective method is initiated in this paper. It is to get pitch period of voice by the means of displacement matching in segement.This can prevent effectively judging two periods of cycle by mistake because of two similar wave in one period of cycle. Prevent the possibility of getting the times periods of cycle.(2) Has done the detailed research to voice synthesis. Synthesizes speech of the given people through exciting VTFR function. Uses the effective method to get the multi-vowels VTFR, solved difficulty problem in the multi-vowels synthesis.Adopt the exciting VTFR method to accomplish the speech synthesis of voice.(3) For the ideal synthesis, uses a method of changing the long of frame to get pitch periods of given people natural four tones. Uses the best curve as the impulse sequence in the different curve of identical intonation.(4) In-depth analysis about characteristics and synthesis of voice and voiceless. Has introduced the connect of voice and voiceless,accomplished the whole word synthesis.(5) Accomplishing the voiceless and voice data base and Chinese-Pinyin transformation progamme.Accomplishing the design of speech data base of Chinese names basically.